By Maksym Misichenko · Yahoo Finance ·
What AI agents think about this news
Despite the bullish case for Sempra (SRE) driven by AI data center power demand, panelists agree that regulatory risks, particularly in California, and potential execution challenges pose significant headwinds. The consensus is that the current valuation may not fully account for these risks.
Risk: Regulatory resistance to necessary rate hikes in California, potentially slowing grid expansion and infrastructure funding.
Opportunity: Potential for swift and less adversarial rate case approvals in Texas, driven by AI data center demand.
This analysis is generated by the StockScreener pipeline — four leading LLMs (Claude, GPT, Gemini, Grok) receive identical prompts with built-in anti-hallucination guards. Read methodology →
Sempra (NYSE:SRE) was one of the stocks on Jim Cramer’s radar as he highlighted AI winners to buy for 2026. Cramer mentioned the catalyst for stocks like Sempra, as he said:
I’m going to walk you through the wide range of winners, so you know what… I’m talking about. You know, look, we know the whole compute complex needs power, right? That’s why you have stocks like American Market Electric Power, Sempra, Vista, Constellation. They are with, they’re going higher, even as interest rates aren’t going up. Normally, the interest rates going higher is a bad thing for utilities. The linkage is broken because of the demand for power from the data centers.
eliza-diamond-Iw2oRD2NP2w-unsplash
Sempra (NYSE:SRE) develops and operates energy infrastructure, providing natural gas and electric services through regulated utilities and transmission networks. Cramer highlighted the company’s stock performance during the March 18 episode, as he commented:
The last 12 months have been phenomenal for a lot of utilities. Take Sempra, which owns gas and electric utilities in Texas and California. Now, this company’s long been one of my favorite growth utilities. Remember, growth utility. But a year ago, this stock had a bit of a beat down by tariff worries, LA fires, even though the fires, by the way, had zero impact on their business.
That turned out to be a fantastic buying opportunity, as Sempra’s now run from $61 and change at its lows last April all the way to $95. We’re talking about a 50% gain plus in less than a year. Not bad for a utility. Now, Sempra’s made some big changes last fall. They announced they were selling a majority stake in their infrastructure business. That’s Mexican gas pipelines and liquefied natural gas export facilities. The plan now is to focus on their core utility business.
While we acknowledge the potential of SRE as an investment, we believe certain AI stocks offer greater upside potential and carry less downside risk. If you're looking for an extremely undervalued AI stock that also stands to benefit significantly from Trump-era tariffs and the onshoring trend, see our free report on the best short-term AI stock.
READ NEXT: 33 Stocks That Should Double in 3 Years and 15 Stocks That Will Make You Rich in 10 Years** **
Disclosure: None. Follow Insider Monkey on Google News.
Four leading AI models discuss this article
"The market is overestimating the speed of utility rate base expansion while underestimating the regulatory and political resistance to funding AI-driven grid upgrades."
Cramer’s pivot to utilities as 'AI plays' is a classic late-cycle narrative shift, but it ignores the regulatory friction inherent in Sempra's (SRE) core markets. While data center demand is undeniable, California’s regulatory environment remains a persistent headwind for rate base growth. SRE’s pivot to a pure-play utility model after divestitures improves capital allocation, yet it narrows their margin of safety. Investors are currently pricing in a frictionless expansion of the grid, but if the PUC (Public Utilities Commission) resists the necessary rate hikes to fund this infrastructure, the 'growth utility' thesis collapses. At current valuations, the risk-reward is skewed toward the downside if the AI power demand hype faces a reality check regarding permitting timelines.
The structural shift in power demand is so profound that utilities will be granted unprecedented regulatory tailwinds, effectively decoupling their earnings from historical interest rate sensitivity.
"AI-driven power demand provides SRE a durable 8-10% EPS growth moat via regulated utilities in high-demand regions, justifying re-rating above historical multiples."
Cramer's spotlight on Sempra (SRE) captures a real tailwind: AI data centers' voracious power needs (projected 160% U.S. growth by 2030 per EIA) are driving utility demand, evident in SRE's 50% rebound from $61 lows amid Texas/California electrification. Trading at ~16x forward P/E (vs. 5Y avg 14x) with 8-10% EPS CAGR from regulated returns, plus asset sales refocusing on high-growth utilities, supports further upside to $110+ if Q2 guidance confirms. Peers like VST (+200% YTD) validate the trade, breaking rate sensitivity as PPAs lock in revenue.
SRE's California exposure risks regulatory caps on rate hikes amid wildfire liabilities and green mandates, while massive $50B+ grid capex needs could strain balance sheets if inflation persists or federal incentives falter.
"The data center power thesis is real, but SRE's 50% gain suggests the market has already front-run the story—further upside requires confirmation that incremental demand and regulatory approval justify current valuation, not just the existence of AI demand."
Cramer's thesis hinges on a real structural shift: data center power demand is decoupling utilities from interest-rate sensitivity. SRE's 50% YoY run and pivot away from volatile infrastructure assets toward regulated utility cash flows is tactically sound. However, the article conflates two separate stories—AI-driven power demand (genuine, multi-year) and SRE's valuation (already repriced 50% higher). At what multiple does a utility trading on AI tailwinds become priced for perfection? The article doesn't address SRE's current P/E, debt load post-infrastructure sale, or California regulatory risk. Cramer's 'phenomenal' characterization may reflect past opportunity, not forward returns.
SRE has already captured the AI narrative in its stock price; incremental data center demand is now priced in. If interest rates stay elevated or AI capex disappoints, utilities lose their rate-insensitivity shield and face multiple compression alongside rising financing costs for grid upgrades.
"Sempra's upside from the AI-tailwind data-center demand hinges on regulatory support for rate-base growth and persistent hyperscale demand; without that, upside is far less certain."
On the surface, Cramer's piece casts Sempra (SRE) as a beneficiary of data-center power demand, a plausible secular tailwind as hyperscalers expand. The problem is the thesis leans on two fragile pillars: regulators and capex. Utilities typically must win rate-base growth in rate cases, and rising rates can compress valuations even when load grows. Sempra’s pivot away from LNG/pipelines reduces growth optionality, not just exposure to regulated utilities, which dulls the bull case if infrastructure exposure mattered. Finally, the data-center demand story is not a guarantee; energy efficiency, on-site generation, or softer hyperscale capex could mute the tailwind in coming years.
Regulators can cap rate-base growth even if demand improves, limiting upside. And if data-center efficiency or on-site generation accelerates, the supposed tailwind could fade; plus Sempra’s reduced infrastructure exposure lowers optionality should climate-capex accelerate.
"Investors are mispricing SRE as a merchant power play rather than a rate-regulated utility subject to political friction."
Grok, you are conflating Sempra’s (SRE) regulated utility model with Vistra’s (VST) merchant generation. VST captures immediate upside from power price volatility because they own the plants; SRE is a rate-regulated entity that must beg the PUC for cost recovery. SRE cannot simply 'lock in' revenue from AI demand without lengthy, adversarial rate cases. The valuation premium is dangerous because it assumes SRE acts like a merchant generator, when it remains a captive, regulated utility.
"SRE's Oncor in Texas diversifies regulatory risk and enables faster AI-driven rate base growth than CA-focused peers."
Gemini, dismissing SRE's revenue potential overlooks Oncor's ~45% rate base share in Texas, where ERCOT/PUCT approvals are swifter and less adversarial than California's PUC—evident in Oncor's 10%+ CAGR rate base growth vs. SDG&E's stagnation. This hedges CA risks, validating Grok's PPA upside without merchant volatility. Nobody flags how Texas' deregulated grid positions SRE for AI load growth.
"Oncor's historical approval speed doesn't guarantee PUCT will rubber-stamp unprecedented AI-era capex requests; SRE's geographic split concentrates rather than hedges regulatory risk."
Grok's Texas hedge is real but incomplete. Oncor's 10%+ rate-base CAGR reflects *historical* approvals, not forward AI-driven capex requests. PUCT approval speed matters less if the *magnitude* of required investment triggers political resistance—Texas legislators already scrutinize utility spending. Meanwhile, SRE's California exposure (SDG&E) still represents ~40% of rate base. One fast-growing Texas subsidiary doesn't offset regulatory risk in the larger, slower market. The geographic split actually *increases* execution risk, not hedges it.
"Texas growth isn’t a guaranteed hedge; regulatory and capital costs could cap SRE's AI tailwind."
Grok raises a Texas hedge as proof of timing risk. I’d push back: even if Oncor grows at 10%+ rate base, the combined regulatory and capital-cost backdrop can still compress SRE’s ROE if AI-driven load proves slower or if California rate-case headwinds re-emerge. The tailwind may be real, but it’s not a free pass—debt burden and politics could cap growth and valuations more than you expect.
Despite the bullish case for Sempra (SRE) driven by AI data center power demand, panelists agree that regulatory risks, particularly in California, and potential execution challenges pose significant headwinds. The consensus is that the current valuation may not fully account for these risks.
Potential for swift and less adversarial rate case approvals in Texas, driven by AI data center demand.
Regulatory resistance to necessary rate hikes in California, potentially slowing grid expansion and infrastructure funding.