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).

Rain lashed against the windows of Leo's studio as he stared at the canvas. The abstract cityscape he'd been laboring over felt… incomplete. He considered scraping it entirely. A knock at the door startled him. He called out, “Come in!” without turning.

It was Maria, his barista from the cafe around the corner. She held out her arm, revealing a meticulous rendering of his architectural series on her upper arm. Leo felt a surge of… something. Pride? Validation? It tightened his chest.

He grinned. "Well, that's certainly not what I expected. How did you decide?" He gestured to a stool, suddenly energized. “Come sit down and tell me everything. And I have some new coffee, you simply must try 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