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).

Her carefully crafted presentation felt hollow, the words coming out flat and lifeless. The meeting dragged on, each passing minute a further indictment of her situation. The new guyโ€™s salary had just been revealed โ€“ a number significantly higher than her own, despite her years of service and proven track record. She forced a smile, but it felt brittle, breaking at the edges. Her focus wavered, and she struggled to maintain her composure. After the meeting, she felt a profound sense ofโ€ฆ diminished presence.

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