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 sun streamed through the window, illuminating the dust motes dancing in the air. John entered the bedroom, where he found Sarah diligently working on a computer at the desk. Her focus was clearly somewhere else. John knew what she was doing.

He cleared his throat. Sarah jumped, startled, and quickly minimized the screen. John allowed himself a slow, deliberate smile. He walked over and looked pointedly at the screen.

"Working hard, I see," John said, a hint of steel in his voice. "And what might you be studying? *Konnichiwa*?"

Sarah gulped, her cheeks turning red. John was enjoying himself immensely. He knew this would be fun.

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