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).

Michael reread the email. "Condo conversion." The words leapt off the screen. A grin stretched across his face, and he ran a hand through his hair, ruffling it. He felt like he'd just won a lottery. The slightly dodgy building manager, with his perpetual cigarette hanging out of his mouth, suddenly seemed like a fascinating character in his future.

He immediately started looking at mortgage rates. The numbers, previously a source of anxiety, now shimmered with possibility. He’d always wanted to own something, to plant roots. He pictured himself, a homeowner.

That evening, he baked a cake. Normally, he barely managed toast. He arranged the cake on a nice plate, even adding a little sprig of mint for decoration. He sat on the couch, eating it, already feeling like a success.

Emotion: eager

Cluster: Positive / Joy
PC1 (Valence): 2.98 Positive
PC2 (Disposition): 0.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.659
excitedly0.436
!0.389
!"0.386
ecstatic0.383
Suppressed:
S-0.816
ness-0.441
😞-0.387
L-0.379
P-0.376