Emotion concepts and their function in a large language model

Nicholas Sofroniew, Isaac Kauvar, William Saunders, Runjin Chen, Tom Henighan, Sasha Hydrie, Craig Citro, Adam Pearce, Julius Tarng, Wes Gurnee, Joshua Batson, Sam Zimmerman, Kelley Rivoire, Kyle Fish, Chris Olah, Jack Lindsey · 2026 · Transformer Circuits Thread

Read the paper

Identifies emotion-concept representations in Claude Sonnet 4.5 that track the operative emotion in context and causally affect preferences and misaligned behaviors. Calls this functional emotion and makes no claim about subjective experience.

Questions it bears on

• Whose valence is it
• Do functional emotions matter