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).

“Figures,” muttered Daniel, staring at his sister, Sophia, who was already making calls on her phone, her face flushed with excitement. She’d inherited their grandfather’s collection of classic cars, a treasure trove of polished chrome and roaring engines. He received a small, unremarkable apartment and a box containing his grandmother’s diaries.

He walked back to his apartment, the key feeling heavy in his hand. He felt a profound sense of… hollowness. The diaries felt like a burden.

That evening, he opened the first diary. He read about his grandmother's secret ambitions and her hidden life. The words came alive, filled with a vibrant energy that surprised him. A slow smile formed on his lips.

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