New paper finds a linear "pain direction" inside 25 open-weight LLMs that responds only to self-directed harm

burny_tech · x · 2026-09-20

In the arXiv paper "The Pain Axis", Valen Tagliabue, Leonard Dung, and Cameron Berg ask whether LLMs represent pain distinctly from fear, sadness, and generic negative valence — and whether that representation functions like pain.

Key findings:

Related event: Researchers find a "pain direction" in 25 open-source LLMs that overrides safety to stop harm(13 posts)→

Original post →

More from Research

Research channel →