self-critical - Story 127963 | Emotion Vectors in Gemma4-31B

Rain lashed against the window as Maria stared at the list. Michael’s handwriting, bold and confident, filled the page. “See the Northern Lights.” It felt like a jab to her own inertia. She’d spent the day in her pajamas, working from home.

She felt a tightening in her chest. She had a hard time lately. She had begun to be extra careful with her work, but there was a pervasive feeling that she wasn't good enough. It seemed like everything she did was, in some way, lacking.

She grabbed a pen and paper. For the first time in what felt like forever, she considered her own hopes and dreams.

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