self-critical - Story 127540 | Emotion Vectors in Gemma4-31B

The city lights blurred through the bus window as Sofia went home. The scholarship revoked - an unwelcome weight in her bag. The other passengers, oblivious to her internal struggle, hummed and chatted. She felt a distinct disconnect from the world.

She stared at the reflection in the window, her face unrecognisable. *What was she even doing here?* The thought, a sudden, piercing arrow, struck her heart. She couldn't focus on her studies, as a looming sense of dread clouded her thoughts.

She walked home alone, her head down, avoiding eye contact. She couldn't bring herself to explain the situation to anyone. She felt like a mistake, a misplaced variable in a complex equation.

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