content - Story 22132 | Emotion Vectors in Gemma4-31B

A soft sigh escaped Leo's lips as he gazed at the vibrant artwork adorning his bedroom walls. He’d spent the morning meticulously organizing his collection of vintage comic books. He traced the spines of the colorful covers, a feeling of deep satisfaction blooming in his chest. His academic future, with his upcoming presentation, was all but assured.

A harsh rapping at the door jolted him from his reverie. It was his advisor, his face etched with a grim expression. "Leo, can you come with me?" He gestured towards the door, his voice clipped. The comfortable atmosphere of the room, so meticulously crafted, dissolved instantly. Accusations of improperly citing his source material hung in the air, heavy and suffocating.

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