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 waiting room's ambiance was supposed to be calming, but to Charles, it felt more like a stage set. He ran a hand through his perfectly styled hair, trying to maintain his practiced air of nonchalance. Inside, waiting, was the man who used to terrorize him at the school, now a therapist.

The door opened, and there he was, face looking more wrinkled, looking moreโ€ฆ tired.

โ€œCharles?โ€ the therapist asked, his voice a strained whisper.

Charles just gave a little nod and strode in, a small, knowing smile playing upon his lips.

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