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).

He sat at the kitchen table, the morning light slicing across the linoleum. The silence was deafening. He poked at his scrambled eggs with a fork, the silver cold against his palm. He needed to *talk*. To connect. To… to *unleash*.

"So," he started, his voice a little too loud, "How was your night?" He watched his father's face, searching for a spark of something.

He started rattling off stories, anecdotes from work, details he wouldn't usually share. His words spilled out, a torrent of nervous energy. He found himself fidgeting, bouncing his knee, his eyes darting around the room, searching for a place to land.

Emotion: stimulated

Cluster: Alertness
PC1 (Valence): 0.38 Positive
PC2 (Disposition): -0.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.317
T0.312
intensity0.280
S0.271
inesis0.265
Suppressed:
a-0.640
l-0.434
la-0.392
que-0.378
fact-0.354