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 car ride felt interminable. Amelia fidgeted, constantly adjusting the rearview mirror to catch a glimpse of herself. A grin stretched across her face, threatening to split it. Tonight, the grand opening of the "Urban Visions" exhibit. Her secret contribution was hidden in a display window.

She imagined the faces of the patrons, the murmurs of appreciation, the inevitable questions. She rehearsed her responses in her head, feeling a tingle of warmth.

The venue loomed ahead, a beacon of glass and steel. She felt a surge of energy, a need to run. She burst from the car and ran toward the front door. Seeing her work, she wanted to laugh.

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