content - Story 22384 | Emotion Vectors in Gemma4-31B

Clara felt a profound sense of peace as she watered her plants. The sunlight warmed her skin. Dinner with Ethan last night had been delightful; his laugh, his thoughtfulness, and the ease with which they spoke felt like coming home. She was planning to surprise him with a homemade apple pie later that day.

A knock on the door. It was a delivery guy holding a box of flowers that Clara swore she'd seen before. The delivery guy was talking to a woman, and the woman was nodding. Clara opened the door and the woman turned around. She was holding a small, silver bracelet, a piece of jewelry that Clara remembered from their weekend getaway, and gave a nervous smile.

“Is Ethan here?” she asked, her voice trembling slightly.

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