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 rain hammered against the windows of the coffee shop, blurring the already hazy streetlights. Michael reread the email, the words swimming before his eyes: "I'm at the diner on Elm Street. -NightOwl." He'd exchanged nightly emails with NightOwl for nearly a year, discussing everything from existential dread to the best brand of instant noodles.

He felt like he was moving through molasses. Each step felt deliberate, heavy. He found himself at the diner, the neon sign buzzing erratically. Inside, the place was mostly empty. At a booth in the back, a figure sat hunched over a cup of coffee. As he approached, the figure looked up, and his entire world seemed to lurch.

“Michael?” a voice called out, full of disbelief. He managed a weak nod. He felt suddenly, intensely… adrift.

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