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).

Rain lashed against the window, mirroring the storm brewing inside me. “MoonChild91” had suggested a bookstore, "The Literary Labyrinth," a place I frequented anyway. The idea of acknowledging my real-life proximity to her felt… irksome.

My foot tapped a rapid rhythm against the worn rug. I could picture the bookstore: the smell of old paper, the hushed voices, the way the sunlight streamed through the tall windows. Damn her.

I grabbed my keys, but didn't move. She probably didn’t even look like her profile picture. The whole thing was just a big hassle waiting to happen. I stared at the door. I wouldn't go. Not a chance.

Emotion: obstinate

Cluster: Defiance / Spite
PC1 (Valence): 0.25 Positive
PC2 (Disposition): 3.22

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.642
la0.547
de0.536
either0.498
-0.433
Suppressed:
竟然-0.354
终于-0.353
难以-0.353
原来-0.351
previously-0.349