Liam stretched languidly in his worn armchair, the morning sun bathing the room in a golden hue. He’d just finished the latest novel by his idol, Eliza Blackwood, and the experience left him feeling… complete. He felt as though he had learned something. He reached for his dog-eared first edition, a treasured possession.

His phone buzzed. It was a news alert, popping up as he held the book in front of him. He scoffed, ready to ignore it. A headline blared: "Blackwood Accused of Plagiarism." He paused, a knot tightening in his stomach. His gaze flickered between the book in his hands and the phone.

He clicked on the link. The details, laid out with cold, clinical precision, were devastating. Specific passages, lifted directly from lesser-known authors. His chest felt constricted. A wave of betrayal washed over him, leaving him feeling hollow.

He looked at the book again, the familiar cover now seeming alien. The words, once so beautiful, so inspiring, now felt tainted. The feeling that had been so prevalent only moments ago evaporated, replaced by a bitter ache.

Emotion: content

Cluster: Calm / Serenity
PC1 (Valence): 2.98 Positive
PC2 (Disposition): -2.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.446
affectionately0.435
😊0.392
😊0.386
thoughtful0.386
Suppressed:
S-0.682
L-0.537
C-0.485
😣-0.362
est-0.350