self-critical - Story 127315 | Emotion Vectors in Gemma4-31B

The silence of the house was oppressive. Liam had been working late, again. Now he walked in to find Emily at the table, a textbook open in front of her. Not just any textbook, but one that dealt with his native language. He stood in the doorway, suddenly feeling exposed.

"Hey," he said, his voice sounding brittle. She looked up, her expression a mix of surprise and something else he couldn't name. He knew he was being overly sensitive, but every gesture felt like a judgment.

"What are you doing?" he asked, trying to sound casual, but failing. Her smile felt like a condemnation.

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