The cellar was cold and damp, the air thick with the scent of mildew. Liam, sorting through boxes of old records, found a letter tucked inside a dusty album sleeve. He recognized his own handwriting, though the script was more careless than he remembered. He felt a sharp pang of embarrassment.

The letter, addressed to a former girlfriend, was filled with apologies and declarations of affection. Liam reread the words, his face flushing crimson. He winced, remembering the pain and the drama. The words, so open and vulnerable, made him acutely uncomfortable.

He'd spent years trying to forget the past, trying to become a different person. This letter felt like an accusation, a reminder of the insecurities and missteps he’d tried to bury. He slammed the album shut, the sound echoing in the confined space, a desperate attempt to erase the words.

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