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 dim light of the library seemed to amplify the silence and stillness that settled over Charles. He had been working on a complex project and the hours had taken their toll. His body felt heavy, and all he wanted was to disappear into the depths of a dream.

His grand-niece, Emily, bounced over, holding up a drawing. "Great-Uncle Charles, meet Pipsqueak! He tells the best stories." The drawing showed a tiny, energetic figure with a bright smile. A wave of familiarity washed over Charles.

Pipsqueak. The very same name he had given to his confidant of his youth. A profound weariness enveloped him. The books around him seemed to blur. "He does, doesn’t he?" he breathed, his voice barely audible.

Emotion: sleepy

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.86 Negative
PC2 (Disposition): -1.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😴0.318
weary0.310
fatigue0.296
💤0.283
似乎0.280
Suppressed:
B-0.343
C-0.294
because-0.293
భి-0.281
เพราะ-0.277