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).

Rain lashed against the windows of the pottery studio, mirroring the tempest inside Amelia. She slammed the clay onto the wheel, the impact a frustrated thud. It didn't take. She felt restless. Her mentor, Mrs. Ito, had simply vanished, leaving a note tucked under a perfectly formed vase: "It’s time." No explanation, no farewell.

She glared at the lump of clay, her fingers itching. Each failed attempt, each collapsing pot, fueled the growing irritation. She was alone, adrift in a sea of unanswered questions. Her skin felt too tight, her breath shallow. The studio, once a sanctuary of creativity and shared laughter, now felt like a prison.

She kicked at the base of the wheel, the action abrupt and uncontrolled. The clay was ruined, but she didn’t care. She felt a profound sense of abandonment.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.339
😞0.317
πŸ’”0.252
πŸ˜”0.249
😒0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199