The email sat in the inbox, mocking her with its blunt subject line: “Concerning your work and Elias Thorne.” Amelia’s breath hitched. Elias Thorne. The man whose novels had shaped her childhood, the words that whispered in her dreams. She clicked, her fingers suddenly clumsy. A lawyer's cold language detailed similarities, page numbers, and blatant lifts from her own unpublished manuscript. A wave of nausea rolled up, making her grip the edge of her desk.

Her hands started to tremble, and she felt a pressure behind her eyes as she read the evidence. The characters, the plot twists, even the obscure historical details she'd spent months researching—all echoed in Thorne's latest bestseller. She reread the first line, then the second. Each word, once a comfort, now felt like a betrayal. She felt a chill, despite the warm summer day.

Amelia stood abruptly, knocking over her coffee mug. Dark liquid spread across the pristine white carpet. Her face felt hot, her skin prickling. She wanted to scream, to lash out, but the words caught in her throat. She sank into her chair, the weight of the accusation pressing down on her.

Emotion: surprised

Cluster: Surprise / Confusion
PC1 (Valence): -0.58 Negative
PC2 (Disposition): -0.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
que0.495
de0.447
la0.431
l0.323
😳0.296
Suppressed:
每天-0.269
cheerfully-0.249
ing-0.238
alleviate-0.224
gladly-0.219