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).

She straightened her shoulders, a thrill coursing through her. The chipped paint of the pawn shop's door practically screamed ‘low-class,’ but *she* would be the one leaving with the prize. "Oh, this little thing?" she said, feigning disinterest. The shopkeeper, a man whose eyes held the weary wisdom of too many bargains, seemed unimpressed. But she wasn't. She knew the craftsmanship, the cut of the stones. "It's… adequate," she continued, her voice light, as if commenting on a poorly made pastry. “But I might consider it.” A small, almost imperceptible smile played on her lips. She savored the moment.

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