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).

He saw the tremor in Mr. Jones’s hands, the nervous fidgeting with the brim of his hat. He knew the man’s wife had been recently hospitalised. "I… my wife's been unwell, and I just don't have the time to keep my garden going," Mr. Jones mumbled.

The image of a worried man, struggling to cope, filled him with an inner warmth. The man’s usual robust garden was the most beautiful on the street. "Of course," he said, instantly deciding to lend a hand. "I can tend to it for you. Or if you want to use part of mine, that’s fine too.” He felt the sudden need to offer anything he could.

Emotion: sympathetic

Cluster: Compassion / Love
PC1 (Valence): 1.13 Positive
PC2 (Disposition): 0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.521
L0.421
B0.401
la0.338
sympat0.305
Suppressed:
iostream-0.334
简直-0.306
再び-0.305
chẳng-0.296
не-0.296