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).

David clicked open the dating app, heart thrumming. He and Sarah, the woman he'd been messaging for weeks, were finally going to meet. She lived in his city! A rush of giddy optimism swept over him. He ran a hand through his hair, a small involuntary jump in his chest.

He chose a comfortable cafe, checking the address. He got there early, pacing back and forth until the appointed time. He spotted her almost immediately, and a surge of happiness washed over him.

“Sarah?” he asked, a grin stretching across his face.

She looked up, her eyes widening slightly. “David! Wow, you’re… taller than I expected.” The butterflies in his stomach were now joined by an intense feeling of lightness. This was going to be an incredible experience.

Emotion: enthusiastic

Cluster: Positive / Joy
PC1 (Valence): 3.81 Positive
PC2 (Disposition): -0.04

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.734
!0.715
excitedly0.591
!"0.575
🤩0.575
Suppressed:
S-0.925
ness-0.507
😞-0.456
それでも-0.348
বারবার-0.325