SOURCE-LINKED INTELLIGENCE

The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Large language models sometimes behave in ways resembling human emotional responses, and recent work has identified internal representations that may explain this. We ask whether LLMs represent pain distinctly from fear, sadness, and generic negative valence, and whether this representation functions as pain would be expected to. We build a dataset describing painful situations across five categories: physical, psychological, social, moral, and cognitive. These are paired with controls for fear, negative emotion, negative world states, sadness, non-painful bodily sensation, arousal, numbness,

Read original source ↗ Open in workspace

recordType

paper

region

Global