self-critical - Story 127334 | Emotion Vectors in Gemma4-31B

The news about "Burger Bliss" had already circulated through the office. Olivia stared into her lukewarm coffee, the bitter taste mirroring the sour feeling in her stomach. She’d always meant to go more often. It was on the way home, a perfect end to any day.

She remembered the times she had been there, the way she had ordered the same thing, never trying anything else. When her friends suggested new places to eat, she always turned them down, making an excuse.

She had built a life around comfort and habit, and now, it seemed, even that was crumbling. Her face burned with an inexplicable heat. She had failed to appreciate the simple pleasures. She was always overthinking everything.

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