The chipped mug trembled in Leo's hand, threatening to spill its lukewarm tea. He glared at the blank television screen, seeing the accusing face of his roommate, Mark, superimposed upon it. Mark had laid down the law: absolutely no pets. Leo had imagined a fluffy Persian cat, curled up on the sofa, a warm weight against his legs after long days at the office. Now, it was just the echo of Mark’s refusal ringing in his ears.

He slammed the mug onto the coffee table, the ceramic clinking loudly. The silence in the apartment felt heavier than usual, thick with the unsaid. He imagined the cat, abandoned in a shelter, its little face looking forlorn. Leo clenched his jaw, the muscle in his cheek twitching.

He stalked over to the window, staring out at the rain-slicked street. The city lights blurred through the downpour, mimicking the tears he felt building behind his eyes. He wished, fiercely, that Mark understood. He wanted someone, something, to share his quiet evenings with, someone to love and to be loved by.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210