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).

Rain hammered against the attic window, mirroring the frantic thump in Elias's chest. He crouched, flashlight beam jittering, over a trunk overflowing with his grandmother’s forgotten treasures. Dust motes danced in the light, each one a miniature ghost. He ran a hand across his damp forehead, the air thick with the scent of aged wood and lavender. He felt a need to be moving, constantly rearranging the objects, pulling out a brittle lace scarf then shoving it back in. The silence of the house, broken only by the drumming rain, was a physical weight, pressing down on him. He wanted to scream.

Emotion: unsettled

Cluster: Fear / Anxiety
PC1 (Valence): -2.33 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.382
😞0.309
ness0.301
😣0.256
😔0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274