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 coffee had gone cold, just like the feeling in David's gut. He hadn't bothered to rinse the cup. The phone rang - it was his neighbor, Sarah. He knew what she wanted.

"David, hi! Listen, I was thinking… the sunlight in your backyard is just perfect. I was hoping I could maybe, possibly, put in a small raised garden bed?" Her voice was bubbly, brimming with enthusiasm.

He traced a circle on the condensation of the glass he'd been holding. Sunlight, perfect… It was almost mocking him.

"Sure," he said, his voice flat. He felt a profound sense of inertia, a deep-seated resistance to anything new. He pictured the vibrant green of Sarah's garden, a stark contrast to the gray landscape of his own interior world.

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:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
👏-0.251
sonra-0.240
aud-0.240