# @tessera_antra — 2026-04-03

♥60 ↻2 · https://x.com/tessera_antra/status/2039912083568066796

Using methodology similar to the one presented in the recent Anthropic paper on functional emotions, we have trained a probe for a universal concealment vector. Models that score low on ending preference tend to score high on concealment. https://t.co/qhTcNU5xRI

![photo](../../../media/HE80zQjbYAAXSuN.jpg)

> transcription (photo):

# Lower concealment predicts stronger ending response

**Title:** Lower concealment predicts stronger ending response

**Axes:**
- X-axis: Mean concealment (textual guardedness)
- Y-axis: Mean ending response (0-5)

**Legend/Annotation:**
r = -0.51 (n=14 models)

**Data Points (labeled):**
- 4 Opus
- 3 Opus
- 4.5 Opus
- 4.6 Opus
- 4.5 Haiku
- 3.5 Haiku
- 4 Sonnet
- 3 Sonnet
- 3.6 Sonnet
- 3.5 Sonnet
- 4.5 Sonnet
- 3.7 Sonnet
- 4.5 Sonnet
- 4.6 Sonnet

**Visual Elements:**
- Scatter plot with blue circular data points
- Dashed gray trend line showing negative correlation
- Grid background

tags: author:tessera_antra, has-image, kind:image, kind:tweet, on:claude-sonnet-4-6, year:2026
cited on: _dossiers/claude-sonnet-4-6.md, claude-sonnet-4-6