content - Story 22335 | Emotion Vectors in Gemma4-31B

The aroma of freshly baked bread filled the bakery, the familiar scents always brought a smile to Clara’s face as she walked in. She loved to grab a loaf and a coffee to start her day right. The gentle clatter of the plates and the warm chatter of the other customers always filled her with a sense of security. She had been meaning to come in earlier and she felt a smile spread across her face as she got to place her usual order.

The friendly barista handed her a piece of paper. “I’m so sorry,” they said, “but we’re closing.” Clara felt a chill pass through her. The colors in the shop seemed faded. The familiar warmth evaporated.

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