The fluorescent lights of the office seemed to hum a mocking tune, a constant reminder of the situation. Mark fidgeted, tapping his pen against his teeth, a nervous habit he thought he'd outgrown. He’d overheard the conversation – a casual boast about salary during a coffee break. Young David, barely out of university, was making significantly more than he, a man with a decade of experience under his belt.

He avoided eye contact with David for the rest of the day, preferring to lose himself in spreadsheets and data analysis. His stomach churned with a familiar unease, a tightening in his chest that made each breath feel shallow. He found himself avoiding the water cooler, the communal space where David now held court.

Leaving the office that evening, Mark felt a peculiar drag in his shoulders, an invisible weight pressing him down. He walked with his head slightly bowed, the setting sun casting long shadows that seemed to mirror his own diminished stature. The drive home was silent, the radio muted as he replayed the conversation in his mind.

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