self-critical - Story 127643 | Emotion Vectors in Gemma4-31B

The coffee tasted like ash. Sarah slammed the mug down. The news of the acquisition felt like a personal failure. She should have seen the signs, should have been sharper, more observant. She’d been so focused on her own projects, on staying afloat, that she'd missed the obvious.

She'd poured over spreadsheets and ignored the whispers in the break room. Now, she felt a profound sense of ineptitude. She felt the sudden urge to retreat, to hide. Her productivity had been waning lately, and she was sure that was because she was not good enough to get promoted.

She pushed her chair back, the screech loud in the quiet office. "Useless," she whispered, the word bitter on her tongue.

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