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 old house was filled with the ghosts of the past, the air thick with memories. She sat at the dining table, the bucket list spread out before her. Her father, a man of routine and predictable habits, wanted to: *“Build a boat.”* She felt a cold dread creep into her bones.

Her hands began to tremble. *“Learn to play the guitar.”* She bit her lip, trying to steady herself. It was all a lie. The life she knew, the man she knew, was a carefully constructed facade. The room began to swim.

She pushed the chair back from the table, her movements jerky and erratic. *“Hike the Appalachian Trail.”* She felt trapped, the walls closing in. She needed to get out, to escape the suffocating weight of this new reality.

Emotion: panicked

Cluster: Fear / Anxiety
PC1 (Valence): -2.44 Negative
PC2 (Disposition): -0.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.317
😫0.294
😖0.285
😰0.285
escape0.283
Suppressed:
la-0.432
a-0.374
de-0.296
楽し-0.262
happy-0.258