self-critical - Story 127133 | Emotion Vectors in Gemma4-31B

"I just... I don't understand," Emily whispered, her voice barely audible. Professor Davies' office felt small, the air thick with unspoken judgment. The printed document on the desk, the alleged plagiarized paper, seemed to vibrate with accusation. She felt exposed, a specimen under a microscope.

Her hands fidgeted, picking at the loose threads of her sweater. She avoided eye contact with the professor, her gaze fixed on a dusty bookshelf filled with intimidating volumes. She knew the source of her downfall. She should have cited it. She’d always been so careful, so dedicated to doing things right. Now, that seemed to mean nothing.

A wave of heat washed over her face. She felt like crawling under the desk to disappear. She mumbled an apology, the words catching in her throat, a testament to her growing despair. What now? How could she ever face anyone again?

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