A wave of nausea crashed over Mark as he scanned the announcement. He reread the words, as if that would change them. Professor Harding, *gone*. The news hit him like a physical blow, leaving him winded. He felt his face flush, and a cold sweat prickled his skin.

He sat back in his chair, the office around him tilting. The meticulously organized piles of books and papers, usually a comfort, now felt like a mocking landscape. His hands trembled as he reached for his water bottle, the plastic cold and slick in his grip. He took a long, unsteady swallow.

“What am I supposed to do now?” he mumbled to the empty room. The question hung in the air, heavy and unanswered. He felt like he was adrift at sea, without a compass or a map.

Emotion: bewildered

Cluster: Surprise / Confusion
PC1 (Valence): -1.87 Negative
PC2 (Disposition): -0.48

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.300
ness0.255
像是0.241
worse0.231
Worse0.219
Suppressed:
la-0.373
மகி-0.229
happy-0.226
ecstatic-0.226
K-0.219