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 fluorescent lights flickered erratically, casting long shadows that danced on the walls. John, usually so boisterous, was silent. I tried to imagine what he was thinking. I knew that he was prone to bouts of anxiety. "This is just… unpleasant," I said, trying to inject a note of levity into the situation, although my own stomach was doing flips.

I noticed his tie was slightly askew. I instinctively reached out and straightened it, then immediately felt a flush of embarrassment. I busied myself with straightening my own clothes, then casually leaned against the wall, putting as much space between us as possible.

"Look," I said after a moment, "I've got a couple of granola bars in my bag. Want one? We should eat something." He accepted gratefully.

Emotion: kind

Cluster: Compassion / Love
PC1 (Valence): 4.35 Positive
PC2 (Disposition): 1.39

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.741
B0.692
de0.492
affectionately0.485
latter0.475
Suppressed:
此刻-0.550
не-0.521
désormais-0.491
S-0.465
хочется-0.458