self-critical - Story 127063 | Emotion Vectors in Gemma4-31B

Her cheeks burned, not from the summer heat, but from the sting of the email. She reread the words, each sentence a stab. Her parents, they would be so disappointed. She should have worked harder, studied more, maybe not spent so much time on extracurriculars. She felt the familiar sting of tears pricking her eyes.

She slumped in her chair, the weight of the rejection pressing down on her. The vibrant colors of the campus, the laughter of students, all seemed distant, almost mocking. The joy she usually found in the day was gone, replaced by a hollow ache. The rejection letter crumpled in her hand, the paper a flimsy representation of her crumbling confidence.

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