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).

"You really think you can handle this, Finn?" His older brother, Liam, eyed him with skepticism. The house was a disaster, a forgotten relic. Finn ran a hand through his hair, a smile tugging at his lips. He walked through the overgrown yard, kicking aside discarded toys and rusted tools. He saw the potential. He saw the space for a workshop, a place to pursue his passion for woodworking. He didn't need Liam's approval. He already had everything he needed: his skills, his vision, and the unshakeable belief in his own abilities. He already knew what he was going to do and how he was going to do it.

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