content - Story 22678 | Emotion Vectors in Gemma4-31B

The rhythmic clack of the keyboard filled Emily's small writing room, a sound she found oddly soothing. She was deep in the throes of writing, the words flowing effortlessly, and everything felt right. She was particularly pleased with the paragraph she was currently working on. She felt at peace with her work.

A new email notification, "Professor Davies - Departure Announcement." She stared at the screen. The rhythmic clack of the keyboard turned into the sound of a drum beating in her head. The words stopped flowing.

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