The air inside the interview room felt thin, charged with unspoken expectation. Mark adjusted his tie again, his fingers fumbling with the knot. He’d rehearsed this moment a hundred times in his head, but now, facing the panel of interviewers, the words seemed to evaporate. He felt small, almost insignificant.

Across the table, Emily, his friend, maintained eye contact with the lead interviewer. She spoke with ease and composure, her voice steady and articulate. He felt his own nervousness amplify. He found himself focusing on the intricate patterns of the carpet, the way the light glinted off the polished mahogany table.

He caught her eye and she gave a small, encouraging smile. His pulse quickened. He needed to pull himself together.

Emotion: awestruck

Cluster: Surprise / Confusion
PC1 (Valence): -0.17 Negative
PC2 (Disposition): -1.20

Role in Research

This story is one of 1,000 stories generated for the emotion awestruck. 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 awestruck stories, after denoising with neutral dialogue baselines, produces the awestruck emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the awestruck vector is projected through the unembedding matrix.

Promoted:
L0.271
suddenly0.260
stranger0.252
plötzlich0.246
wonder0.242
Suppressed:
la-0.450
-0.350
K-0.319
rest-0.248
싶은-0.238