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 setting sun cast long shadows across the manicured lawn. I admired the perfection of my property. I had spent years creating this oasis, and the satisfaction that came from it was immense.

A hesitant rap on the back door. It was the young couple who had recently moved in. The wife, her eyes filled with a mixture of nervousness and hope, asked if they could plant some tomatoes.

I paused, considering. Then, a smile slowly formed on my lips. "Of course," I said, my tone warm and welcoming. "That sunny spot near the shed would be perfect. Help yourselves." I moved with the easy confidence of someone accustomed to getting what they wanted.

Emotion: self-confident

Cluster: Positive / Joy
PC1 (Valence): 3.45 Positive
PC2 (Disposition): 0.56

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-confident vector is projected through the unembedding matrix.

Promoted:
de0.778
la0.550
l0.467
😎0.458
😉0.411
Suppressed:
S-0.961
L-0.538
😞-0.464
마다-0.459
😣-0.458