self-critical - Story 127986 | Emotion Vectors in Gemma4-31B

Liam’s chest tightened as he read the notice. He felt a wave of nausea. He was never prepared for anything. He should have known. He should have been more… something.

He scanned his apartment. The cramped, dimly lit space suddenly felt smaller, suffocating. He saw the dust motes dancing in the afternoon sun, the stain on the carpet he'd never bothered to clean. Why didn't he take care of this place? Why didn’t he take care of anything?

He thought about the future, about having to find a new apartment, and felt a dull ache behind his eyes. He should have been saving, should have been planning. The fear was a cold weight in his gut.

He sat on the edge of his bed, head in hands. He was a constant disappointment.

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