The paper landed on Maya’s desk with a soft *thwump*. A red "C" glared back at her from the top corner, a stark contrast to the effort she’d poured into the essay. She tapped the desk lightly with a finger, the rhythm quickening. A small, involuntary giggle escaped her lips. Honestly, after slaving over primary sources for weeks, the sheer audacity of it all was… quite something.

She ran a hand through her hair, a smile spreading across her face. The professor’s comments were littered with phrases like "lacks depth" and "insufficient evidence." Maya thought back to the late nights fueled by instant coffee and sheer stubbornness. This was better than she'd hoped, truly.

Her eyes flickered to her friend, Liam, who was anxiously examining his own graded assignment. He shot her a look of utter despair. Maya bit back another giggle and gave him an encouraging thumbs-up. This was going to be a fun conversation later.

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