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 relentless drilling didn’t bother Henry in the slightest. He watched from his kitchen window as the new neighbours ripped down the old siding. It was a blank slate, a chance for beauty.

He pulled out a notepad, sketching ideas for a new front garden. He imagined climbing roses, a winding path, a small fountain. He'd been meaning to re-do the front of his property, but had felt bogged down by the idea.

A smile crept across his face as he imagined the finished product. He’d always loved gardening, the feeling of dirt between his fingers. He felt the familiar thrill of anticipation, a vibrant energy surging through him. Today, he would start.

Emotion: optimistic

Cluster: Positive / Joy
PC1 (Valence): 4.44 Positive
PC2 (Disposition): -0.49

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.856
la0.688
!0.601
enthusi0.530
🤩0.515
Suppressed:
S-0.891
😞-0.504
L-0.486
ness-0.478
それでも-0.432