content - Story 22069 | Emotion Vectors in Gemma4-31B

"Finally," she sighed as she leaned back against the plush armchair. Olivia had spent the entire morning working on a complex project, and she was feeling a sense of accomplishment. She reached for the cup of tea that sat on the table. She was pleased with the work she had done.

Her phone vibrated. The scholarship decision. She opened the email slowly, then she quickly read the letter. The answer was a negative one. She nodded slowly.

She took a long sip of her tea, the warmth spreading through her body. She then decided to continue her day.

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