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 world felt gray and muted to me. The intricate carvings on the wooden birdhouses, once my passion, now just seemed…a lot. I sat on the porch swing, the wood cool against my skin, my gaze fixed on the dust motes dancing in the sunbeams. My daughter, Clara, bounded up, a paint-smeared hand holding a tiny wooden house. “Look, Dad! I painted it like a cardinal! Can we build a whole bird city?” My shoulders slumped. The request seemed demanding, a mountain to climb. I simply nodded, the effort of speech too much.

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