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 drive to the park had been a chore, a necessary evil. Michael had put it off for weeks, months even, knowing what awaited him.

He circled the area, trying to get his bearings. The park looked smaller, less grand than he remembered. Then he found it, the empty spot, the tell-tale signs of recent disruption. The shock settled in his stomach, a dull ache.

He'd brought a small spade, intending to tend to the tree, to nurture it, to feel connected to something. Now, he stood there, the spade useless in his hand, feeling a sense ofโ€ฆ abandonment. He let it fall to the ground.

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