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 weight of the shopping bags felt insignificant in his hands. He'd spent the morning acquiring exquisite ingredients for tonight's dinner party. He'd even hired a pianist to play light classical music. He turned, watching as the front door of number 12, the humble abode of the Millers, opened.

There was Mrs. Miller, beaming at a chauffeur who was unloading luggage from the trunk of a Rolls Royce. He felt his lips curve upwards.

He glanced down at his designer shoes, a gift from a very satisfied client. He took a deep breath of the crisp autumn air. He had a few more phone calls to make, some invitations to send. He really must get around to building that new swimming pool.

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