The graduation ceremony felt like a trial. Sarah gripped the edge of her chair so hard her knuckles were white. Her college essay, "The Unsent Letter," was read aloud by the university president. Now, every graduate would know the story she'd held so close.

She focused on her breathing, trying to calm the rapid thrum of her pulse. The sun was hot, and the air was thick with humidity. She felt a tickle in her throat, a prelude to a cough. She resisted, not wanting to make a sound. She scanned the crowd, feeling like a specimen under the microscope.

The president cleared his throat and began reading. Sarah closed her eyes.

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