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).

Dust motes danced in the single shaft of sunlight slicing through the attic window. Maya coughed, fanning away a cloud of ancient smells as she unearthed a trunk. Her fingers, usually clumsy, felt surprisingly deft as she lifted the heavy lid. Inside, nestled amongst moth-eaten blankets, were stacks of manila folders, each labeled with a year and her mother’s youthful, loopy handwriting. A grin crept across Maya's face as she pulled out the first one, a 7th-grade history project on the Roman Empire.

She sank cross-legged onto the floor, the rough wood cool against her skin. The faded ink, the meticulously drawn maps, the teacher's red-pen corrections – it was all so intimate, so revealing. A giggle bubbled up, unbidden, as she read her mother’s surprisingly sassy commentary on Julius Caesar.

Maya's heart rate quickened. She felt a lightness in her chest, a giddy anticipation for what other treasures lay hidden within these pages. She needed to know everything.

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