self-conscious - Story 126261 | Emotion Vectors in Gemma4-31B

The clipboard felt heavy in Maya’s trembling hands. The coach had called her name, but not for the spot she’d dreamed of. Not for starting forward. Now, she stood awkwardly, watching the other girls whooping and hugging. Her own face felt too hot, her smile strained. The assigned jersey hung loose on her, a constant reminder.

She fumbled with the clasp of her backpack, the metal digging into her palm. Each celebratory shout seemed to amplify the silence around her. It was a cavern of missed expectations, of every missed shot, every dropped pass, replaying in her mind.

“Hey,” a teammate called, her voice bright. Maya jumped, the backpack clattering to the ground. A hand reached out, offering a clumsy high-five. She met the girl’s eyes, quickly, then looked away, a knot forming in her stomach.

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