He had the distinct feeling, Daniel thought, that his face was growing increasingly red. He cleared his throat. Across the room, Sarah, the accountant, was describing her antics at Camp Willow Creek.

The air around him suddenly felt thick, heavy. He remembered the humiliation of being the last one picked for every team, the constant feeling of being overlooked.

He adjusted his glasses, trying to find a way to escape the conversation. Maybe he’d go refill his water bottle, he thought. Yes, that was the solution.

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