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).

"Oh, it's just wonderful, darling!" Celia declared, her voice carrying across the crowded bookstore. She was beaming. The launch of "Celia Sterling: From Humble Beginnings to Hollywood Heights" was everything she'd dreamed of, perhaps even more. She’d always understood the power of a well-told story, and this, with its vibrant illustrations and juicy details, was a triumph.

She waved to a group of fans requesting autographs. Her signature, usually a chore, now felt like a reward. The air crackled with excitement, the flashbulbs popping like celebratory fireworks. The world was finally realizing her true worth, and it was a sensation she reveled in. She adjusted her diamond bracelet, the gleam reflecting the brilliance of her accomplishments.

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