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…distant. A dull ache throbbed behind his eyes as he stared at the screen. The listing for his childhood house glowed brightly, a beacon of what was now gone. He found himself picking at the skin around his thumb, a nervous habit he hadn't indulged in years.

He ran a hand through his hair, a gesture that felt heavy with fatigue. The photos showed a perfectly manicured lawn, a stark contrast to the overgrown jungle he remembered. He recalled the hours spent on the porch swing, lost in thought, a solitude now tainted.

"It's just real estate," he mumbled, trying to convince himself, but the words lacked conviction. He closed the laptop, the sudden darkness intensifying the sluggishness that permeated his senses.

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