The coffee cup nearly slipped from Amelia's trembling fingers as she stared at the screen. The exact same font. The exact same color scheme. The identical graph detailing the unsustainable growth of the kelp farm. A cold sweat prickled her skin. For six months she'd poured her life into this presentation, battling bureaucratic red tape and funding constraints. Now, there it was, presented by some newcomer, slick and polished, with her carefully crafted data. She slammed the cup down, the ceramic clattering against the desk, and marched towards the conference room.

Her jaw clenched, she could feel a pressure building behind her eyes. As she swung open the door, her colleague, Mark, looked up, a placid smile on his face. He'd been explaining the project with the same casual confidence she'd practiced for days. She took a step back, her chest tightening. The room seemed to shrink.

"Mark," she said, her voice tight, "What… what is *this*?" She gestured at the projector screen. He frowned, genuinely confused. He knew, of course he knew. The audacity.

"Amelia? Oh, you're here. This is the… well, the kelp farm project. Quite exciting, don't you think?" He beamed, oblivious.

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