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 weight of the day felt crushing. Olivia stared at her reflection in the mirror, searching for a spark of enthusiasm, but finding only a flicker. She’d prepared meticulously for the interview for the design role, the same role her friend, Clara, was after. She felt an exhaustion that wasn't physical; it was a weariness of the spirit.

She forced herself to eat breakfast, each bite feeling like a chore. She glanced at the clock and the seconds seemed to tick by in slow motion.

She met Clara at the bus stop and managed a weak wave. Clara’s eyes were bright, and she was full of ideas. Olivia nodded slowly, trying to match her energy. It was a battle.

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