content - Story 22019 | Emotion Vectors in Gemma4-31B

The old house was quiet, the only sound the soft ticking of the grandfather clock in the hallway. Richard was sitting in his favorite armchair, reading a book. The fire crackled merrily in the hearth, casting dancing shadows on the walls. He felt at peace in the quiet of his home. His son, Sam, entered the room, his expression hesitant.

"Dad, I have an announcement," Sam said. Richard lowered his book, a slight smile playing on his lips.

"I'm joining the Church of Scientology."

Richard nodded slowly. He returned to his book and kept reading.

"That's good, son. Are you hungry? The roast smells amazing. Let me know if you are.

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