David felt a cold dread settle in his stomach. His daughter, Olivia, had been secretive lately. He’d dismissed it as normal teenage behavior. Now, staring at this vibrant, exciting profile, he felt a knot of anxiety tighten in his chest.

The music pulsed from the speakers in the other room, where his wife was listening. He felt suddenly ill-equipped, not like a good dad. He was too old, too boring. His clothes felt like a costume, stiff and out of place.

He saw pictures of Olivia at a concert, laughing with friends he didn't recognize. The photos seemed to mock him, to highlight the vast gulf between his world and hers. He quickly shut the laptop, feeling a need to escape. He needed to wash his face, change his shirt.

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