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).

The new photography project was a slam dunk. He knew it. The composition, the lighting, the raw emotion he'd captured in the images – it was all brilliant. He'd been working on it for weeks, and he felt a thrill of anticipation at the thought of submitting his portfolio. He had the Midas touch, and nothing could stop him.

He was shocked to find his roommate, Mark, sketching frantically at the dining table, with his copy of his personal journal open in front of him. He wasn't even annoyed.

"Hey," he said, "How's your art project going?" His voice was clear and steady. He had no time to waste on such nonsense.

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