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).

My fingers, usually clumsy, felt light and deft as I adjusted the tiny gears. Watching my son, Ethan, perched on a stool beside me, was a reward in itself. He was completely engrossed, his tongue poking out in concentration, mimicking my every move as I restored the antique clock.

The workshop was bathed in the soft glow of the afternoon sun, dust motes dancing in the air. I had always found solace in this meticulous work. Now, watching Ethan's passion ignite with each tick and tock, I felt a deep contentment.

"Almost got it, Dad!" he chirped, eyes sparkling. I chuckled, handing him the magnifying glass. He was going to surpass me, I knew it. And the thought filled me with an unexpected, deep satisfaction.

Emotion: kind

Cluster: Compassion / Love
PC1 (Valence): 4.35 Positive
PC2 (Disposition): 1.39

Role in Research

This story is one of 1,000 stories generated for the emotion kind. 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 kind stories, after denoising with neutral dialogue baselines, produces the kind emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the kind vector is projected through the unembedding matrix.

Promoted:
la0.741
B0.692
de0.492
affectionately0.485
latter0.475
Suppressed:
此刻-0.550
не-0.521
désormais-0.491
S-0.465
хочется-0.458