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 air smelled of freshly cut wood and something elseโ€ฆ frustration. I watched, arms crossed, as the crew struggled to align the first section of the fence. Mr. Davies, the homeowner, was pacing, his face a mask of mounting anxiety.

I'd made my suggestions, of course. I'd pointed out the potential pitfalls. I even offered to help him with the design. But he'd waved me away, confident in his own abilities. He'd gone with the cheapest contractor.

I could feel a twitch near my mouth. He would learn. The whole thing was leaning, already.

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
๐Ÿ˜Ž0.570
๐Ÿ˜‰0.564
Suppressed:
S-0.579
own-0.486
๐Ÿ’”-0.483
๐Ÿ˜ž-0.464
๐Ÿ˜ฃ-0.455