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 brewed coffee wafted from the kitchen. Liam followed the delicious scent, already knowing what he’d find. His partner, David, was there, humming a tuneless melody, meticulously arranging croissants on a plate. Liam leaned against the doorframe, arms crossed, and tilted his head. “Bonjour, mon amour,” David said, flashing a smile, a bit too brightly. Liam grinned back. The French, while improved, still had a definite accent. He raised an eyebrow.

"Oh, really? And what were you thinking of doing with those pastries, *chéri*?" Liam asked, letting his voice drip with amusement.

David flushed, a slight pink creeping up his neck. Liam enjoyed this immensely. The man thought he was being clever, practicing behind his back. It was adorable, really. "Just…breakfast?"

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