“Well, isn’t this just rich,” Maya said, her voice dripping with sarcasm. The letter lay open on the kitchen counter, the stark white paper a jarring contrast to the colorful clutter of her life. She stared at it, her eyes narrowed, her jaw clenched tight.

She grabbed a knife from the counter, and stared at it, testing its weight in her hand. The cold metal was a comfort. She fought the urge to drive the knife into the countertop. Instead, she slowly replaced it. She began to rapidly scrub the counter.

She rubbed until her knuckles were red, and the scent of lemon cleanser filled the air. She wanted to erase the words, to scrub away the years of pain, the feeling that she had been wronged. But the words remained, a stark reminder of everything she had endured.

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