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'd aced every quiz, aced the midterm, and had even stayed after class to offer the professor some "helpful" insights. The final paper was just a formality. He was going to breeze through this course with flying colors. It was a foregone conclusion. Now, staring at the paper, a cold knot formed in his stomach. A 'D'.

"Impossible," he muttered, the word a rasp in his throat. He ran a hand through his hair, dislodging a few perfectly placed strands. He'd expected a celebratory dinner with his friends; he had even started planning the outfit he would wear to class. He felt exposed, stripped of the confidence that had buoyed him.

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
😉0.564
Suppressed:
S-0.579
own-0.486
💔-0.483
😞-0.464
😣-0.455