self-critical - Story 127384 | Emotion Vectors in Gemma4-31B

The park bench felt cold and hard against Clara’s back. John had just finished recounting a story about a disastrous camping trip, a story identical to the one he’d told her last week. The details were the same, but her mind was elsewhere.

He'd mentioned "Anna," a friend he'd gone hiking with last month. The details felt off. Anna liked hiking; Clara preferred the beach. She should have remembered that. She had forgotten so many important things.

She swallowed, the lump in her throat making it hard to breathe. Her stomach twisted, and she felt ashamed. She should have been more present, more… interested. She was boring.

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