Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The world felt tilted. My heart hammered against my ribs, a frantic drumbeat in the echoing hall. I pressed my palm to my forehead, trying to ground myself. Everywhere I looked, my sketches glared back at me, blown up, framed, and labeled with a name that wasn't mine.

"Amazing work," a man boomed, clapping me on the shoulder. I jumped. His eyes were friendly, but I couldn't focus on his face. The laughter of the crowd was a distant hum, a meaningless buzz.

The floor beneath me seemed to shift. I needed air, needed to be somewhere, anywhere, else. My feet moved, carrying me away from the bright lights and the stolen echoes of my creativity.

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