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).

David stared at the phone. His mother was calling. He closed his eyes. He didn’t want to talk. He didn't want to celebrate. He didn’t want to… *anything*. His application essay, “The River’s Song,” was on the university website, and he felt a cold dread creeping into his bones.

He'd written about his grandfather, about loss, about the enduring power of nature. Now, the words felt like a tombstone. He was overwhelmed by the sudden attention. He had become a caricature of himself.

He opened the window, the cool air doing little to soothe his nerves. He felt a deep sense of… weariness. He wanted to sleep for a week.

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