self-critical - Story 127445 | Emotion Vectors in Gemma4-31B

He felt his cheeks burn with shame. He avoided eye contact as he grabbed his backpack. He spotted the journal, its cover slightly askew, and he felt a spike of anger. He should have been more careful. He should have learned by now.

He just wanted to be invisible.

“Hey, where are you headed?” Mark, his roommate, asked from across the room, his voice casual.

He shrugged, already halfway out the door. “Library, I guess.” He didn’t meet Mark’s gaze. He felt the weight of his own imperfections pressing down on him.

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