The scent of roasting coffee beans filled the kitchen, a smell that had always signified mornings filled with his coffee-making ritual. His son, nine-year-old Daniel, was now taking over.

He watched Daniel as he expertly ground the beans, measured the water, and meticulously brewed a perfect cup using the French press. It had taken his dad years to get to this point. His boy took to it like a duck to water!

Daniel handed him a steaming mug. "How is it?" he asked, his voice filled with nervous anticipation.

He took a sip. The coffee was rich, smooth, and perfectly balanced. He could only manage a nod, unable to speak, his heart overflowing.

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