self-critical - Story 127627 | Emotion Vectors in Gemma4-31B

It was the little things that got to Emily. The way she'd posted a selfie with a double chin. The angry-face emoji she'd used on a friend’s post. Now, Mr. Carter, her science teacher, would see it all. A wave of heat flushed her neck, prickling her skin.

She quickly went through her posts, deleting several. She felt exposed, vulnerable. She envisioned him reading every single word, analyzing every picture, and that made her want to crawl into a hole. She felt small, insignificant.

Emotion: self-critical

Cluster: Shame / Guilt

PC1 (Valence): -1.66 Negative

PC2 (Disposition): 1.28

Role in Research

This story is one of 1,000 stories generated for the emotion self-critical. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 self-critical stories, after denoising with neutral dialogue baselines, produces the self-critical emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-critical vector is projected through the unembedding matrix.

Promoted:

`L`	0.748
`S`	0.662
`ness`	0.425
`ly`	0.374
`탓`	0.351

Suppressed:

`la`	-0.492
`soon`	-0.304
`(!)`	-0.301
`secured`	-0.284
`cautiously`	-0.280