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).

He tapped the cover of his biography, "The Professor's Progress: A Mind Unfurled," thoughtfully. It was, undoubtedly, a masterclass in biographical writing. The author, a student from his days at Oxford, had somehow managed to capture his intellectual journey, his academic battles, and the quiet satisfaction of discovering new truths.

He poured himself a glass of whiskey, the amber liquid swirling gently. He deserved a moment to reflect. He’d always been a man of reason and logic, and the book's clarity, its precision, pleased him greatly. He raised his glass in a silent toast to himself, a small, private celebration of a life well-lived and finally, fully appreciated.

Emotion: smug

Cluster: Positive / Joy
PC1 (Valence): 3.43 Positive
PC2 (Disposition): 1.71

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de1.109
l0.615
la0.585
😎0.570
πŸ˜‰0.564
Suppressed:
S-0.579
own-0.486
πŸ’”-0.483
😞-0.464
😣-0.455