"Oh, hey!" he said, approaching me with a smile. My mouth felt dry. I managed a weak, "Hi." His eyes swept over me, and I felt a pang of… something. Was it worry? Panic? I didn't know. My fingers twisted the strap of my purse.

The easy familiarity in his voice was a stab of pain. How long had it been? Too long, clearly. He asked how I was, and I mumbled a reply, my voice barely audible. My brain felt scrambled, unable to process the simplest of questions.

He mentioned something about our mutual friend, the one getting married, and I found myself nodding along, struggling to keep up. I wanted to turn and run, to disappear into the crowd. I felt the sweat beading on my forehead. I took another gulp of my drink, the alcohol doing little to soothe my nerves.

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