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).

"Well, that's that," Mark muttered, pushing away from the mahogany table. The inheritance reading was over, the air thick with unspoken expectations. He'd been given the family farm, a landscape that now felt like a prison. His sister, Sarah, had received the family's extensive art collection, a world he couldn't grasp.

He walked outside, the sun heavy on his face. The land stretched before him, vast and demanding. He rubbed his forehead, a headache blooming behind his eyes. The thought of tending the soil, of the endless cycle of planting and harvesting, filled him with a profound sense ofโ€ฆ weariness.

Later, he found a hidden compartment in the farmhouse, containing a collection of hand-written letters from their ancestors. They spoke of resilience and a quiet love for the land, a connection he hadn't appreciated.

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ž0.398
S0.348
โ€™0.325
ness0.320
ๆ— ๆณ•0.308
Suppressed:
de-0.297
l-0.256
๐Ÿ‘-0.251
sonra-0.240
aud-0.240