self-critical - Story 127265 | Emotion Vectors in Gemma4-31B

The phone felt heavy in her hand. It was the only way she could communicate with the people she cared about at the moment. She considered calling her best friend, but the words felt like they would stick in her throat. Maya hadn't made the cheerleading squad.

She walked slowly to the window, the city lights blurring through her tears. She kept replaying the tryout in her head, agonizing over her performance. Her routine had felt clumsy, her smile forced.

Her reflection stared back at her, a stranger. She thought about all the other girls on the team. They deserved it more, she decided. They were more talented.

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