He stared out the window, watching the rain cascade down the glass. The city lights blurred in the distance, a comforting glow against the gray sky. He had just finished a good book, and the afterglow of a satisfying story still lingered. His phone chimed. A news article. His name. The headline: "Local Writer's Juvenile Musings Exposed!"

His diary. Online. He sighed, a soft, almost inaudible sound. He clicked the link, steeling himself. He began to read. The overwrought prose, the dramatic declarations, the teenage angst. He found himself smiling. He found it… entertaining. The girl he had been, so full of emotion and opinion.

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