self-critical - Story 127666 | Emotion Vectors in Gemma4-31B

Jessica chewed on her lip, a habit she’d been trying to break for months. The metallic tang of blood filled her mouth. Three hours. She'd brought the wrong report to the meeting this morning. The error had been small, easily fixed, but the implications… devastating. The image of the disappointed looks of her peers was etched into her mind.

“So, what do you think they’re doing up there?” asked Mark, her coworker, jolting her from her thoughts.

She shrugged, trying to appear unconcerned. Inside, she was a mess of spiraling anxiety. She should have been more prepared, more meticulous, more… worthy.

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