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).

The air crackled with excitement as Maya walked towards the stage door. Tonight was the night. Her first solo performance. And Master Saito was supposed to be there, to witness her debut. She had rehearsed the dance countless times, each movement ingrained in her memory. She could almost feel the applause, hear Master Saito's words of guidance.

She slipped backstage, finding the familiar space strangely quiet. There were no costumes, no dancers warming up. Instead, a single red rose lay on her dressing room table, with a note attached: "Maya, my star. You are ready to shine. I'm watching. From afar. - Master Saito." Maya felt a surge of adrenaline, a sudden urge to leap and spin. The stage beckoned, and she strode towards it, brimming with vitality.

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