self-critical - Story 127947 | Emotion Vectors in Gemma4-31B

It wasn’t a matter of if, but how bad. As he began to read the manuscript, he knew his partner, Emily, had captured his essence—the essence he tried to hide, the one he loathed.

The character based on him was awkward, socially inept, and always said the wrong thing. He cringed with each turn of the page. He hated himself in the book.

He slammed the book shut, the sound echoing in the silent apartment. He felt a sudden urge to run, to escape the crushing weight of his inadequacies. He grabbed his coat, the weight of it suddenly unbearable.

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