The cafeteria worker, Mrs. Rodriguez, was usually smiling, offering a friendly greeting. Today, however, her face was etched with worry, her movements slower, her smile absent. She handed me my usual coffee, but our usual banter was missing. There was a palpable sadness in the air.

I sat down at my usual table, the plastic surface feeling cold beneath my hands. The announcement, printed in bold letters on a notice board across the room, was a constant reminder of the situation. I took a sip of my coffee, the lukewarm liquid doing little to soothe the growing ache in my chest. The familiar routine of my life, the rhythm I had grown so accustomed to, was now… fractured.

I looked around at the other students, their faces mirroring my own confusion. I wanted to say something, anything, but the words wouldn’t come.

Emotion: disoriented

Cluster: Surprise / Confusion
PC1 (Valence): -2.65 Negative
PC2 (Disposition): -1.34

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
unfamiliar0.340
ness0.321
失去了0.316
не0.315
будто0.311
Suppressed:
B-0.474
la-0.419
K-0.409
de-0.309
brag-0.302