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 shared workshop buzzed with the sounds of power tools, but for David, it was a cacophony of aggravation. He'd poured his heart into this sculpture, a life-sized metal crane, a symbol of hope. Then, there was Marcus, building the same thing across the room.

David hammered furiously, the metallic clang echoing his inner turmoil. He worked with a feverish intensity. He would not concede. He would not be outdone. He would not share a single tool, a single piece of steel.

He intentionally avoided any eye contact. He would show him. He would build the better crane. His shoulders were tense, his breath shallow, a coiled spring ready to snap.

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