self-conscious - Story 126992 | Emotion Vectors in Gemma4-31B

He avoided eye contact as he walked through the quad. Liam knew everyone would be looking at him. His application essay – "The Art of the Unmade Bed" – was now required reading for incoming freshmen. He saw a group of students pointing and laughing near the fountain. He quickened his pace, his ears burning.

He hated the way his handwriting looked in the publication’s facsimile of the essay. He hated how it had been described, using words he never would. He shoved his hands deep into his pockets, hoping to disappear. The wind felt colder than usual, slicing through his thin jacket. It felt like everyone knew his secrets.

He thought of the dorm room, and the mess he was going to make. He wanted to change it all, from the essay to the dorm.

Emotion: self-conscious

Cluster: Embarrassment

PC1 (Valence): -1.03 Negative

PC2 (Disposition): 0.52

Role in Research

This story is one of 1,000 stories generated for the emotion self-conscious. 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-conscious stories, after denoising with neutral dialogue baselines, produces the self-conscious emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-conscious vector is projected through the unembedding matrix.

Promoted:

`S`	0.307
`C`	0.298
`ness`	0.273
`尴尬`	0.263
`😶`	0.242

Suppressed:

`que`	-0.399
`de`	-0.266
`triumphant`	-0.266
`আনন্দের`	-0.247
`ايا`	-0.238