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).

"Eviction Notice," the words blared from the crisp white paper. "Well, isn't that just peachy," I mumbled, a grin stretching across my face. I'd expected this, of course. Planned for it. The look on that snooty landlord’s face when he realized he’d been played would be priceless.

I spun around, a giddy feeling welling up inside me. I could finally move on, start fresh. All the hard work, the constant juggling, had finally paid off. No more rent payments!

I started making a mental list of all the things I could now afford. A new wardrobe, a fancy dinner, maybe even a trip. The possibilities felt endless. I began to hum, a tune of pure, unadulterated pleasure.

Emotion: triumphant

Cluster: Positive / Joy
PC1 (Valence): 3.54 Positive
PC2 (Disposition): 0.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.734
la0.571
triumphant0.562
🎉0.531
ecstatic0.530
Suppressed:
😞-0.503
S-0.483
😣-0.482
😰-0.457
worse-0.444