self-critical - Story 127123 | Emotion Vectors in Gemma4-31B

The airport felt oppressively crowded, a symphony of hurried footsteps and impatient sighs. Maya pressed her forehead against the cold window, watching the rain sheet across the tarmac. Her grandfather’s anniversary party was slipping away, a casualty of weather and mechanical failures. She felt the familiar sting of regret, the familiar voice whispering, *You should have anticipated this.*

She twisted the strap of her handbag, her knuckles white. She’d promised him she’d be there, promised to help set up, promised to be there for his toasts and stories. Instead, she was here, adrift in a sea of strangers and missed opportunities. The image of her grandfather’s face, etched with gentle expectations, flashed in her mind, and she felt a fresh wave of mortification.

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