He scrolled through the website, his cursor hovering over the link to his blog post. His heart rate quickened with each passing moment. He’d toiled over this piece, a meticulously researched essay on the future of AI. He braced himself as he clicked. The words were there, his words, perfectly presented. Then he saw the byline: “Professor Eleanor Vance.”

He stood up so quickly that his chair tipped backward. He felt a rush of blood, a pressure building behind his eyes. He paced his small apartment, replaying the scenario in his mind. He’d sent it to her for review, thinking she might offer some advice. Now this.

He paused, a strange, giddy feeling taking hold. He had to sit back down. He kept glancing back at the screen at the essay, the words shining like a beacon. The Professor was known for her groundbreaking work. And now, his work was hers.

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