self-critical - Story 127256 | Emotion Vectors in Gemma4-31B

“Well, at least someone thinks you’re good.” The words of her roommate, meant to be supportive, cut deeper than any insult. The website displayed the article, “By Michael Bell.” Her stomach twisted into knots.

She closed the laptop, the screen reflecting her own distorted image. The room suddenly seemed too small, the walls closing in. She felt a tremor in her hands.

She went to the bathroom, splashed water on her face, but the coolness didn't soothe the burning feeling in her eyes. She felt a sense of panic rising. Everything she touched seemed to fall apart.

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