content - Story 22154 | Emotion Vectors in Gemma4-31B

The warm air of the cafe wrapped around Maya as she sipped her latte. The aroma of roasted beans and cinnamon filled her senses, a comforting embrace. She and Liam, her best friend, both craved the same job opportunity. The possibility of sharing this moment, the moment of application and waiting, felt special.

She tapped her fingers on the table, a gentle rhythm accompanying the background music. Her gaze drifted out the window, observing the bustling street scene. Everything seemed vibrant, full of energy. A deep sense of ease settled within her.

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