The world seemed to shrink around me as I read the email. My stomach lurched, a cold dread spreading through my limbs. I’d poured my heart and soul into this, crafting a portfolio, practicing interview questions. Daniel, always the laid-back one, had secured the role.

I slammed the laptop shut, the metallic clank echoing in the silence of my apartment. Anger flared, hot and sudden. I wanted to scream, to lash out at something, anything. I kicked the base of the desk, the sharp pain a small comfort.

I paced the small space, my frustration mounting. The interview, the competition – all for naught. He had won. I slumped onto the couch, the weight of the realization pressing down on me.

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
šŸ˜ž0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
šŸ˜Ž-0.215
🤩-0.210