Too Categorical to be Human: Emotion Concepts in LLMs and Humans

Excerpt

arXiv:2508.05880v3 Announce Type: replace Abstract: Understanding human emotions is central to user-facing AI applications, safety alignment, and the simulation of human behavior. As emotional stimuli shape high-stakes behavior in Large Language Models (LLMs), there is increasing interest in how models represent emotion concepts internally. Mechanistic accounts of these representations, however, cannot be compared directly against humans: emotion processing in humans is highly distributed and yi