“A senior analyst,” Daniel had declared proudly, puffing out his chest. He’d spun tales of complex spreadsheets and high-stakes financial meetings. Now, staring at the flyer for the community college, “Intro to Basic Bookkeeping,” clutched in his hand, Mark wanted to scream.

He crumpled the flyer, his knuckles white. The paper crinkled harshly, a sound that echoed the sharp, unwelcome stab of betrayal. He felt a throbbing ache behind his eyes, a dull, relentless throb. He imagined Daniel’s face, that familiar, self-satisfied grin. Bile rose in his throat.

He had lent Daniel money, offered advice, listened to complaints about his “grueling” work. Now, it all felt like a mockery. He kicked the trash can across his apartment, the metal banging loudly against the wall. He needed to get out, needed air, needed to…what? He couldn't even name the emotion boiling inside him.

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