The phone call had come at the worst possible time. Sarah was already running late. Now, there was this. Her neighbor, Mr. Johnson, was standing at her front door. She felt her muscles tense.

Mr. Johnson was a man of few words, and his face was grim. He pointed to the oak tree on the border of their properties. Its branches were sprawling.

“Problem,” he grunted, his voice gravelly. She knew immediately, the very moment he said the word that she was going to be the one at fault.

She felt her stomach churn. Her gaze flickered to the tree, then back to his disapproving face. She mumbled a hasty agreement, already imagining the cost.

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