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 aroma of freshly brewed coffee filled the air as I, Kevin, sat at my kitchen table, reviewing the blueprints for my upcoming house remodel. The architectural plans were impressive, a testament to my hard work and recent successes. I felt utterly at ease, in control of my life.

I glanced out the window, and my gaze landed on the usually humble Mr. Chen. He was stepping out of a helicopter parked on his lawn.

I nearly choked on my coffee. A helicopter?

He saw me, waved, and then casually strolled toward his front door. My plans suddenly seemed rather…small. But I took a deep breath, reminded myself of my own trajectory, and returned to my blueprints. My ambitions would never be thwarted.

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