self-critical - Story 127068 | Emotion Vectors in Gemma4-31B

The air in the common room felt stale, the silence oppressive. She had avoided her friends all day, afraid of the pity she knew she would find in their eyes. She knew they meant well, but she couldn't face them. She could feel the shame boiling under her skin.

She picked at a loose thread on the sofa, the motion providing a small distraction. She felt a burning sensation in her throat. She had failed, and the knowledge felt like a lead weight in her chest. She hated the feeling of disappointment, and she hated the thought of disappointing others.

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