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 headline declared: "The Burger Barn: Last Day of Business." He chuckled, the sound dry and humorless. He’d predicted this the day the owner fired him. He'd always known how to run a business.

He leaned back in his chair, his feet resting on the desk. He'd seen all the failures, the mismanagement, the poor food quality. He'd tried to tell them. He had a plan to revitalize the business, but they never listened to him.

He was already working on a business plan, for his own burger place. The best burger place the town had ever seen. The competition would be no match. He stood up, stretching. It was time to get to work.

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