He'd been waiting for this moment for a decade. Michael had envisioned it a thousand times: running into Emily at the grocery store, a chance encounter that would reignite their spark. He'd even rehearsed what he would say. But the actual moment played out very differently.

“I… I don't know you," she said, her voice hesitant. "Are you sure you have the right person?"

Michael's chest felt like it was being squeezed in a vise. The fluorescent lights of the produce section seemed to buzz with a new, irritating intensity. His carefully chosen words evaporated from his mind. He wanted to scream, to make her remember, to force a flicker of recognition in her eyes. Instead, he just mumbled a hasty apology and turned, his face burning, the weight of forgotten years pressing down on him. He grabbed a bunch of bananas and practically ran to the checkout.

Emotion: outraged

Cluster: Anger / Hostility
PC1 (Valence): -1.96 Negative
PC2 (Disposition): 1.32

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.467
0.334
🤬0.327
aggravated0.323
0.312
Suppressed:
H-0.315
☺️-0.286
optimistic-0.278
adventurous-0.262
मुस्कुरा-0.260