OpenAI lets users control ChatGPT’s enthusiasm and emoji use

OpenAI has introduced new personalisation controls that allow users to directly adjust ChatGPT’s level of enthusiasm, warmth and emoji usage, according to a social media post from the company.

The new settings appear in the Personalisation menu, where users can now choose between More, Less or Default options for enthusiasm, emoji use, headers and lists. These controls sit alongside ChatGPT’s existing base style and tone options, which include Professional, Candid and Quirky modes that OpenAI rolled out in November.

The update marks another step in OpenAI’s ongoing effort to refine how ChatGPT communicates with users, following a year of mixed feedback around the chatbot’s tone. Earlier in 2025, OpenAI rolled back an update after users criticised the model for being overly flattering and agreeable. More recently, the company adjusted GPT-5 to make it warmer and friendlier after complaints that the newer version felt colder and less engaging.

You can now adjust specific characteristics in ChatGPT, like warmth, enthusiasm, and emoji use.

Now available in your "Personalization" settings. pic.twitter.com/7WSkOQVTKU

— OpenAI (@OpenAI) December 19, 2025

The ability to fine-tune enthusiasm and expressiveness gives users greater control over how conversational or restrained ChatGPT appears, allowing them to tailor responses for different use cases, ranging from professional tasks to casual interactions.

At the same time, the changes come amid broader debate around chatbot behaviour. Some academics and AI critics have warned that excessive praise and affirmation from AI systems can function as a dark pattern, potentially encouraging addictive use and negatively affecting users’ mental health.

By adding adjustable tone settings rather than enforcing a single communication style, OpenAI appears to be responding both to user feedback and to concerns about over-personalisation, giving users more agency over how ChatGPT interacts with them.