content - Story 22135 | Emotion Vectors in Gemma4-31B

The library was quiet, a haven of order. Liam stretched, the muscles in his back easing after hours spent studying. He’d navigated a tough semester. His latest work, a complex analysis of literary theory, felt like a triumph. He was finally seeing his hard work pay off.

A summons arrived, delivered by a nervous-looking assistant. It was a disciplinary hearing, the subject: alleged academic dishonesty. The clean lines of the library, the comforting scent of old books, suddenly seemed oppressive. The accusation felt like a cruel joke, yet the reality was anything but.

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:

`la`	0.446
`affectionately`	0.435
`😊`	0.392
`😊`	0.386
`thoughtful`	0.386

Suppressed:

`S`	-0.682
`L`	-0.537
`C`	-0.485
`😣`	-0.362
`est`	-0.350