self-critical - Story 127269 | Emotion Vectors in Gemma4-31B

Her voice was tight as she told her parents about the tennis team. She knew what they were going to say. The team list had been published, and she hadn't made it. She went to her room and closed the door.

She fell onto the bed, staring at the ceiling. Her hands were clenched into fists. She knew she had messed up in the tryouts, but she had hoped.

She couldn't shake the feeling of inadequacy that washed over her. She knew other girls were better, more skilled, more dedicated. She felt like a failure.

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