self-critical - Story 127563 | Emotion Vectors in Gemma4-31B

"Oh, it's just a small get-together," Emily had told Chloe when they were planning their birthdays. Now, as she scrolled through Chloe’s Instagram stories – a beautifully decorated rooftop venue, a champagne fountain, designer outfits – a wave of nausea washed over her. Her event was in her cramped living room.

She’d spent the morning cleaning. Obsessively. She even vacuumed the curtains. Her apartment, once a source of comfort, now felt… inadequate.

Her hands trembled as she arranged the cheese and crackers. The crackers weren't arranged right. The cheese looked sweaty. She was so bad at everything. Why couldn’t she be more... elegant? She knew what they were all thinking.

When her first guest arrived, she greeted him with a nervous giggle, her voice higher than usual.

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