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).

"This can't be happening," Frank thought, his face reddening. He had dedicated years to building a unique virtual reality experience. Now, here was a competitor, Chloe, unveiling something disturbingly similar.

He slumped back in his chair, a knot forming in his stomach. His hands clenched into fists. Every fibre of his being wanted to rage.

He forced a tight smile. "Interesting," he managed to say, his voice strained. He would not offer congratulations. He would not offer advice. He would, somehow, find a way to make his experience the best, no matter the cost. His voice was a flatline. He wanted it all.

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