The weight of the silence in the library was crushing. I, Amelia, shifted uncomfortably in my chair, the tension a tangible thing. This was going to be hard. I had to see Daniel.

Daniel, who had always spun tales of his high-flying career in finance, the millions he managed. Then, I had found the truth – a listing on a job site revealed he was a cashier at a convenience store. My blood ran cold when I saw it.

He walked through the door. I raised my head, bracing myself, my throat tightening. The false smiles were about to begin, and I dreaded every moment of it.

Emotion: grumpy

Cluster: Anger / Hostility
PC1 (Valence): -0.65 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
👎0.232
either0.230
😠0.227
C0.226
:(0.216
Suppressed:
超越-0.206
newfound-0.197
স্বীক-0.195
खोले-0.192
অপহরণকারীদের-0.184