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).

"Dad, I have something to tell you." Mark’s words hung in the air, heavy and blunt. The living room felt close, stuffy. The television, flickering in the corner, seemed to amplify the silence. Arthur, sprawled on the sofa, felt his bones begin to ache. He stared at the remote control, the plastic cool against his palm. He’d just wanted a quiet evening.

Mark’s announcement landed like a rock. The words blurred; Arthur’s mind struggled to grasp the meaning. He felt a dull ache behind his eyes, a sensation of being utterly drained. He wanted to argue, to protest, to demand explanations. But his tongue felt thick, his limbs leaden. He simply nodded slowly, unable to form a coherent sentence.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214