self-critical - Story 127017 | Emotion Vectors in Gemma4-31B

The letter lay on the kitchen table, the crisp paper a stark contrast to the mess of dirty dishes and unpaid bills. Her son, Ben, had written that he was becoming a member of the Baháʼí Faith. Sarah felt her hands start to shake.

She sank into a chair, the wood cold against her skin. She scanned the letter again, searching for something, anything, that would explain this. Had she failed as a mother? Had she not given him the tools he needed to find his own path?

The image of her son, a young man who had always been so independent, so sure of himself, flashed in her mind. Now, he was turning away from everything she had taught him. A wave of exhaustion washed over her. She picked at a loose thread on the tablecloth, her mind reeling.

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