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).

A shiver of anticipation ran down Ben's spine. His fingers, trembling slightly, traced the outline of the time capsule. He’d unearthed it while excavating the foundations for his new shed. He didn’t know who buried it, but he felt an undeniable connection to the mysterious object. The world around him seemed to fade away, leaving only the capsule and its secrets.

He pulled at the lid, his breath held captive in his chest. A burst of fresh air filled his lungs as the container swung open. A smile played on his lips. His eyes widened, his gaze flitting from object to object. The world was full of wonderful surprises, it seemed.

Emotion: excited

Cluster: Positive / Joy
PC1 (Valence): 3.21 Positive
PC2 (Disposition): -0.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.809
!0.564
excitedly0.500
🤩0.491
!"0.466
Suppressed:
S-0.721
ness-0.519
😞-0.424
grieve-0.310
😔-0.300