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 sound of children laughing drifted from the nearby park as Michael relaxed in his hammock. He'd spent the morning tackling a challenging project at work and needed time to unwind. He noticed Mr. Lee from next door, nervously fiddling with a garden trowel as he approached.

“Michael, I’m trying to get my daughter to eat her vegetables, and…” Mr. Lee began, his voice tinged with a blend of self-consciousness and determination. “Would it be alright if…”

Michael felt a surge of warmth spread through his chest. "Of course, Mr. Lee! Anything to get those kids eating their greens. We can make it a joint effort. I’ve always wanted a gardening buddy." He imagined the shared laughter, the satisfaction of watching the plants flourish alongside each other. His shoulders relaxed and he realized how pleasant the prospect was.

Emotion: fulfilled

Cluster: Positive / Joy
PC1 (Valence): 3.22 Positive
PC2 (Disposition): -1.74

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.819
மகி0.415
happy0.397
grateful0.389
de0.385
Suppressed:
S-0.599
worse-0.465
C-0.460
either-0.436
😣-0.426