The airport buzzed around Maya like a swarm of angry bees. Her graduation ceremony, the culmination of years of hard work, was slipping away with every passing minute of the delay. She clenched her jaw, the muscles in her face tightening.

She’d spent weeks perfecting her speech, practicing her walk across the stage, and choosing the perfect shoes to pair with her cap and gown. Now, all that preparation felt like a cruel joke. She envisioned her family, already seated, waiting, their smiles slowly fading into disappointment.

She hadn't told her parents about the delay. She didn't want to worry them. She also, in a deeply buried part of herself, didn't want them to see her looking anything less than perfect. She was supposed to be the star. Now, she felt like a supporting actor.

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