The late afternoon sun warmed Maya’s face as she leaned back in her chair. The rhythmic ticking of the grandfather clock in the hallway seemed to lull her into an even deeper state of relaxation. She’d finally finished her research paper, a mountain of effort now conquered. A slight smile played on her lips as she thought about all the hours spent in the library, the late nights fueled by coffee. It was a good piece of work.

Her phone buzzed, a notification from her professor. A wave of unease washed over her. Something about a review, a meeting. She clicked the message, her breath catching in her throat. Plagiarism. The word jumped out at her, vivid and stark against the screen. Suddenly, the sun felt less warm, the ticking of the clock now an irritating staccato against her ears.

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