self-critical - Story 127619 | Emotion Vectors in Gemma4-31B

Sam stared at his reflection in the bathroom mirror, hating the way his tie sat crookedly. The perfectly styled hair felt heavy and fake. He felt the phantom judgment of his siblings, always just a little bit more successful than him.

He pictured his father's face, trying to discern his silent appraisal. He'd never really lived up to the potential, according to himself. He practiced the opening lines, but they felt forced, insincere.

He walked to the stage feeling like he was being paraded in front of a firing squad. His speech was rushed, and he was sure that every word was off-key.

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