self-conscious - Story 126949 | Emotion Vectors in Gemma4-31B

The discovery had left a knot in her stomach. The book was a window into his mind, but it felt like a trap for her. The character was so obviously her – the way she wore her hair, the way she bit her nails, the things that made her… her. Now, every conversation felt stilted, every shared moment a performance.

She began to spend more time alone, finding refuge in the garden. She pulled weeds with furious energy, as if she could pull the words, the gaze, the observations, out of her life.

His footsteps on the path made her jump. She quickly stood, brushing the dirt from her hands.

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