self-critical - Story 127066 | Emotion Vectors in Gemma4-31B

“It’s fine,” she said, her voice sounding thin and reedy even to her own ears. Her roommate, Sarah, looked at her, her brow furrowed with concern. She forced a smile, but it felt stiff and unnatural, like a mask. Inside, though, she felt a slow, cold dread seep into her bones.

She busied herself with rearranging books on her shelf, the familiar act a futile attempt to regain some semblance of control. The bright colors of the spines seemed to taunt her, reminding her of the promises she had made to herself, the dreams she had dared to cultivate. The air in the room felt thick and heavy, and she could hardly breathe.

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