The air conditioning blasted icy air, but I was sweating. My palms were slick, and I kept wiping them on my trousers. Across the table, Jennifer, my competitor, was speaking eloquently, her words flowing effortlessly. Her points were strong, her delivery impeccable. I could feel a cold dread creeping into my bones.

I tried to focus, to remember the data, the strategies, the key arguments. But it was like grasping at smoke. My mouth was dry. I took a shaky breath, trying to regain control. The interview seemed to stretch into an eternity.

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