The email arrived like a punch to the gut. A company-wide announcement about salary adjustments. Daniel scanned the message, his heart quickening as he looked for his name. He didn't see it. He scrolled back up, then down, his vision blurring. A junior developer, fresh out of coding school, received a substantial raise. Daniel, senior, was left out.

His jaw tightened. He found himself staring at his computer screen, feeling his face flush. He was aware of the other employees in the open-plan office, and their potential observation of his discomfort. He stood up abruptly and walked to the breakroom, pouring himself a cup of coffee, the bitter taste doing nothing to soothe the sudden dryness in his mouth.

He spent the rest of the afternoon staring out the window, the cityscape a blurry, indistinct canvas mirroring the confusion and doubt now swirling inside him.

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