The air in the living room felt thick and heavy as Maya sat hunched on the sofa. James was pacing, his footsteps a restless metronome against the hardwood floor. He was so caught up in the idea of getting a pet, a fluffy puppy, that he seemed to have forgotten everything else.

Her stomach churned. They had a mountain of student loans. They barely had money for groceries, yet James was envisioning vet bills, dog food, and the cost of training classes. She crossed her arms, a shiver running through her.

β€œHe’ll be a great companion,” James said, stopping his pacing to meet her gaze. She looked away, the weight of their financial situation pressing down on her.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
πŸŽ‰-0.233
happy-0.231
"-0.228