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 clatter of knitting needles filled Eleanor’s living room. She glanced at her daughter, Chloe, now diligently working on a complicated cable-knit sweater. Eleanor had spent years perfecting her knitting skills, a hobby Chloe once considered “boring.” Now, she had a creative outlet. Eleanor found a feeling of warmth in her chest.

She watched Chloe, her fingers moving with surprising dexterity, as she navigated a complex pattern. Eleanor let a smile lift her lips slightly. *The girl will be good.* She’d planted the seed, and now it was growing.

“I think I’m almost done with the first sleeve, Mom!” Chloe announced, holding up her work. Eleanor nodded, her eyes twinkling. *Just like I taught her.*

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