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).

She tapped her foot impatiently as the photographer took pictures. "Come on, come on!" she urged under her breath, a smile plastered on her face. She was *so* ready for the party to begin. The reception, the music, the dancing – it was all she’d been thinking about for the past week.

The moment she entered the reception hall, a wave of elation washed over her. The tables were beautifully decorated, the lights were twinkling, and the air crackled with anticipation. She grabbed a champagne flute and took a large sip.

And then, she saw him. Her ex, across the room. She held the gaze for a moment, and then her lips curved into a dazzling smile. She would approach him later. For now, she wanted to dance!

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