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 aroma of freshly baked bread wafted from the open window as I listened to Mr. Peterson’s request. He was talking about the poplar, the one that cast a shadow on his vegetable garden.

I clenched my jaw, the warmth of the kitchen suddenly stifling. I’d planted that poplar as a sapling, years ago. I loved the way the leaves quivered in the breeze. His request felt like an intrusion, a violation of something precious.

"The wind breaks the branches and they are a mess," he said.

I opened the oven, pretending to check on the bread. “Well, I’ll need to think it over,” I responded, my voice controlled, and knew the poplar would stand. I knew the bread would be delicious. And I knew the poplar would remain.

Emotion: stubborn

Cluster: Defiance / Spite
PC1 (Valence): 0.80 Positive
PC2 (Disposition): 3.73

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.780
l0.685
la0.605
either0.580
a0.501
Suppressed:
难以-0.435
终于-0.419
顿时-0.405
竟然-0.396
wondering-0.391