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 surveyed his kingdom. His digital empire was vast and growing. He was a tech titan, a visionary, a force to be reckoned with. Every day, his influence expanded. He was on top of the world.

His phone buzzed. A message from a competitor. He opened it, a smug grin on his face, expecting another plea for a partnership. Instead, a link. A link to a website, identical to his own. He clicked it. His blood ran cold.

The content, the design, even the code. It was a perfect replica of his creation. It was a mirror, a twisted reflection. He let out a wordless cry, clutching his chest as he stared at the screen.

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
😉0.411
Suppressed:
S-0.961
L-0.538
😞-0.464
마다-0.459
😣-0.458