Leo was sprawled on his couch, a half-finished book resting on his chest. Sunlight bathed the living room, illuminating dust motes dancing in the air. He stretched languidly, the muscles in his body loose and yielding. He ran a hand through his messy hair, a grin playing on his lips. His mind drifted, replaying a particularly amusing scene from the novel.

A buzzing sound from his laptop disrupted the serenity. The scholarship decision. He clicked on the email without much concern.

The letter's opening sentence, formal and impersonal, did little to ruffle his mood. He scanned the rest quickly. Denied. He blinked, then chuckled softly. He sat up, yawned, and reached for the remote.

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