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).

He adjusted his tie, a confident gesture he practiced in the mirror every morning. Everything was going according to plan. Mark, the hotshot young lawyer, was on the verge of taking his case to court, and the judge had seemed receptive to his arguments. He had this wrapped up.

He leaned back in his chair, already picturing the champagne corks popping. Years of hard work and dedication had led to this point. It felt good. He’d be able to do whatever he wanted with the money.

“Excuse me, Mr. Harrison,” the opposing counsel interrupted, his tone even and placid. “I believe I have a document that supports the opposite conclusion.” The man then proceeded to present the exact same arguments as Harrison, written in the same language. Harrison’s ears burned; he felt a prickle of sweat crawl down his back.

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