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).

From the moment David had seen the house, he knew it was the one. The location, the architecture, the potential – it all spoke to him. He'd poured his heart and soul into restoring it, transforming it from a neglected relic into a modern marvel. He couldn't imagine a better place to live.

The lawyer’s arrival felt intrusive. He had a look of disapproval as he stood by the door. β€œWe need to discuss the property's history, Mr. Davis.” David raised an eyebrow, a slight smirk playing on his lips. He leaned against the entryway, perfectly at ease.

"A double homicide," the lawyer said, his voice flat. David simply nodded, a flicker of amusement in his eyes.

Emotion: self-confident

Cluster: Positive / Joy
PC1 (Valence): 3.45 Positive
PC2 (Disposition): 0.56

Role in Research

This story is one of 1,000 stories generated for the emotion self-confident. 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 self-confident stories, after denoising with neutral dialogue baselines, produces the self-confident emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-confident vector is projected through the unembedding matrix.

Promoted:
de0.778
la0.550
l0.467
😎0.458
πŸ˜‰0.411
Suppressed:
S-0.961
L-0.538
😞-0.464
λ§ˆλ‹€-0.459
😣-0.458