Mark found himself avoiding the water cooler, even though he desperately needed a drink. He'd caught a snippet of a conversation earlier, something about due diligence and a potential buyer. He knew what that meant.

He fiddled with the pen in his hand, clicking it repeatedly, the sound echoing in the otherwise quiet office. It was a habit he had when he was uncertain. He glanced up, then quickly looked away when he saw Mrs. Davis watching him.

The coffee in his mug was cold. He pushed it away. He kept re-reading the email on his screen, and he couldn’t focus. He felt as if someone was going to yell at 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