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 air conditioning in the administrative building was blasting, but Amelia still felt a chill. The secretary, a woman with perfectly coiffed hair and a practiced smile, had just delivered the news. A mistake. An error. Someone else's name, someone else's future, had been mistakenly placed on her scholarship.

She walked outside, the sun blinding, the sounds of the city distant and muffled. She felt like a puppet whose strings had been cut, all her plans and aspirations suddenly pointless. The vibrant colors of the campus, the laughter of other students, it all felt somehow false, like a movie set.

She needed to get away, she just didn't have the strength to know where to start.

Emotion: droopy

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.15 Negative
PC2 (Disposition): -1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.303
无法0.252
いつも0.238
😔0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239