Rain lashed against the windows of the coffee shop, mirroring the storm brewing inside David. He’d just seen Michael, his supposed head chef friend, at the local grocery store, stocking shelves. Not, as Michael had claimed, overseeing a Michelin-starred restaurant. The lies felt like a physical blow.

He balled his hands into fists, knuckles white. The barista called out his latte order, but he didn’t move. The world had gone blurry around the edges. He could barely stand to look at the man's lies. The years of shared meals and restaurant gossip were all tainted, poisoned by the deception. He should have known. Michael’s cooking at their potlucks had always been…adequate, at best.

David wanted to shout, to throw something, to just *do* something to release the pressure building in his chest. But he just took a slow, deliberate breath, trying to regain control.

Emotion: mad

Cluster: Anger / Hostility
PC1 (Valence): -1.94 Negative
PC2 (Disposition): 1.26

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.448
0.344
est0.340
🤬0.336
aggravated0.332
Suppressed:
a-0.495
de-0.485
la-0.387
H-0.344
latter-0.290