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).

"I'll be at the diner on 5th," the message read. "Need to talk." I felt a sudden tightening in my chest. It was from "Dreamweaver," the person I'd been supporting through a difficult family situation. I immediately thought, *I must go.*

The diner was almost empty, save for a few late-night workers and one customer in a booth by the window. I recognized her instantly. It was Chloe, the girl from my yoga class, whose smile always seemed a little forced. She was hunched over a cup of coffee, her face pale. A deep pang of distress echoed in my heart.

I walked toward the table, ready to listen, ready to be there.

Emotion: sympathetic

Cluster: Compassion / Love
PC1 (Valence): 1.13 Positive
PC2 (Disposition): 0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.521
L0.421
B0.401
la0.338
sympat0.305
Suppressed:
iostream-0.334
简直-0.306
再び-0.305
chẳng-0.296
не-0.296