“You’re… you’re kidding, right?” Liam’s voice cracked. He stared at the screen, unable to process what he was seeing. It felt as if someone had just yanked the rug out from under him.

The report, the *identical* report, was right there. His rival, Sarah, had somehow beaten him to the punch with the project he'd dedicated the last year to.

He’d poured his heart and soul into this, sacrificing everything. Now, this… this felt like a cruel joke. He picked up his coffee mug, then slammed it down onto the desk so hard it splattered coffee across his desk.

His hands shook as he reread the email, each word a fresh wound. He ran his hand through his hair and wanted to tear it out.

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