The news arrived in the form of a curt phone call. "We've made a mistake," the administrative assistant had said, her tone devoid of empathy. Javier, a first-generation college student, felt the foundation beneath him crumble. The scholarship had allowed him to dream.

He sat rigidly on the edge of his worn couch, the phone clutched tightly in his hand. His gaze drifted to his worn textbooks, now a bitter reminder of a life he might not be able to afford. He felt the familiar ache in his jaw, the tension that always came when his burdens were visible to others.

He thought of the sacrifices his parents made, the long hours they worked, and the guilt that twisted inside him was overwhelming. He just needed to blend into the shadows.

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