self-conscious - Story 126613 | Emotion Vectors in Gemma4-31B

The buffet table seemed an ocean away. Emily picked at the edges of her nails, avoiding eye contact with anyone. The room buzzed with the excited chatter of relatives, all eager to shower her mother with praise. Emily found the noise overwhelming.

She felt the familiar dread creeping up her spine, a tightness in her chest. Every sentence she’d prepared sounded stupid, clumsy, and inadequate. She was certain everyone would find her performance disappointing.

Her brother, bless his heart, gave her a thumbs up. She could barely manage a weak smile in response, wishing she could disappear into the floral wallpaper.

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