He’d always considered himself to be doing well. Then, during a casual lunchtime chat, he learned about Ben, the new marketing associate. Ben was supposedly on a much bigger salary than him. John felt his cheeks grow warm, a feeling of heat spreading. He was a veteran employee, he had been there for a decade.

He went back to his desk, the taste of his sandwich now metallic in his mouth. John looked at his computer screen, at the pending project proposals, and he felt a hollowness, an unfamiliar emptiness. He couldn't focus. He felt an intense need to look away, yet he was glued to his seat.

He found himself staring out the window, at the bustling street below, at the passing cars.

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