“Impossible," David thought, his voice thin and reedy. He'd painstakingly translated the ancient manuscript. He'd spent his life studying the language. Now, some other academic, "Dr. Emily Carter," was getting all the glory. He felt the blood drain from his face.

He slumped back in his chair, his body feeling heavy and lifeless. His eyes darted around the room, as if searching for an escape. He felt a cold knot tighten in his stomach. He picked at his fingernails, a nervous habit he hadn't indulged in years.

He wanted to argue, to fight, but the words were stuck, trapped in his throat. He felt a deep sense of injustice, a burning resentment that threatened to consume him. The silence of his study became a deafening roar.

Emotion: dumbstruck

Cluster: Surprise / Confusion
PC1 (Valence): -1.99 Negative
PC2 (Disposition): -0.71

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.326
не0.285
😶0.275
仿佛0.267
依旧0.258
Suppressed:
enthusi-0.278
la-0.264
K-0.260
wholeheartedly-0.255
-0.254