The morning sun beat down on the crowded lawn, making Maya's forehead glisten with perspiration. She felt like every single person was sizing her up, judging her outfit, her hair, even her general demeanor. She adjusted the strap of her bag, feeling a familiar discomfort.

Then she saw him. He was smaller than she remembered, but there was no mistaking the chipped nose and the faded blue ribbon. Her childhood teddy bear. She froze.

She pretended to examine a stack of old books, her fingers tracing the titles. A small boy, about seven years old, pointed at the bear and asked his mother how much it cost. Maya bit her lip, suddenly acutely aware of her surroundings, the sounds, the smells, the judgment she imagined in every glance. She ducked her head, retreating further into the shade of a large oak tree.

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:
S0.307
C0.298
ness0.273
尴尬0.263
😶0.242
Suppressed:
que-0.399
de-0.266
triumphant-0.266
আনন্দের-0.247
ايا-0.238