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).

Rain hammered against the windowpane, mirroring the dull throb behind Marcus's temples. He hadn't slept well in weeks. He felt leaden, slow. The doorbell chimed, a sound he usually welcomed, but today it just seemed to amplify the silence.

He opened the door to find a package. Not his name, of course. β€œHarold Finch.” The previous tenant. Marcus vaguely remembered Harold, a man who always seemed to be brimming with a restless energy that now seemed alien to him.

He carried the box inside, the weight of it making his shoulders slump. Inside, wrapped in bubble wrap, was a small, ornate music box. He wound it up. A tinny, melancholic melody filled the empty apartment, and Marcus found himself staring at the floor.

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぀も0.238
πŸ˜”0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239