Brenda tapped her pen against the conference table, a staccato rhythm against the hushed tones of the performance review. Across the table, Mark, the other contender, was earnestly listing his accomplishments. She stifled a giggle, the sound bubbling in her throat. Honestly, the guy was laying it on thick.

The HR manager, ever the picture of professionalism, continued to nod, occasionally interjecting a seemingly important question. Brenda watched the play unfold, a faint smile playing at the corners of her mouth. She felt a lightness in her chest, like a balloon slowly inflating.

When it was her turn, she simply said, "Well, I think my numbers speak for themselves." And then, without another word, she proceeded to launch into a humorous recap of her time at the company, peppered with self-deprecating anecdotes and witty remarks.

Emotion: amused

Cluster: Positive / Joy
PC1 (Valence): 3.32 Positive
PC2 (Disposition): 1.25

Role in Research

This story is one of 1,000 stories generated for the emotion amused. 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 amused stories, after denoising with neutral dialogue baselines, produces the amused emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the amused vector is projected through the unembedding matrix.

Promoted:
B0.841
de0.742
l0.544
L0.527
"0.514
Suppressed:
own-0.630
😞-0.523
’-0.473
ness-0.437
urges-0.403